EMNLP'2022 Tutorial "Meaning Representations for Natural Languages: Design, Models and Applications"
Instructors: Jeffrey Flanigan, Ishan Jindal, Yunyao Li, Tim O’Gorman, Martha Palmer
Abstract:
We propose a cutting-edge tutorial that reviews the design of common meaning representations, SoTA models for predicting meaning representations, and the applications of meaning representations in a wide range of downstream NLP tasks and real-world applications. Reporting by a diverse team of NLP researchers from academia and industry with extensive experience in designing, building and using meaning representations, our tutorial has three components: (1) an introduction to common meaning representations, including basic concepts and design challenges; (2) a review of SoTA methods on building models for meaning representations; and (3) an overview of applications of meaning representations in downstream NLP tasks and real-world applications. We will also present qualitative comparisons of common meaning representations and a quantitative study on how their differences impact model performance. Finally, we will share best practices in choosing the right meaning representation for downstream tasks.
Introduction to Open Source RAG and RAG Evaluation
Meaning Representations for Natural Languages: Design, Models and Applications
1. Tutorial
Meaning Representations for Natural Languages:
Design, Models and Applications
Jeffrey
Flanigan
Tim
O’Gorman
Ishan
Jindal
Yunyao
Li
Nianwen
Xue
Martha
Palmar
2. Meaning Representations for Natural Languages Tutorial Part 1
Introduction
Jeffrey Flanigan, Tim O’Gorman, Ishan Jindal, Yunyao Li, Martha Palmer, Nianwen Xue
4. Mo#va#on: From Sentences to Proposi/ons
Who did what to whom, when, where and how?
Powell met Zhu Rongji
Proposition: meet(Powell, Zhu Rongji)
Powell met with Zhu Rongji
Powell and Zhu Rongji met
Powell and Zhu Rongji had
a meeting
. . .
When Powell met Zhu Rongji on Thursday they discussed the return of the spy plane.
meet(Powell, Zhu) discuss([Powell, Zhu], return(X, plane))
debate
consult
join
wrestle
battle
meet(Somebody1, Somebody2)
5. Capturing seman.c roles
SUBJ
SUBJ
SUBJ
• Tim broke [ the laser pointer.]
• [ The windows] were broken by the
hurricane.
• [ The vase] broke into pieces when it
toppled over.
6. Capturing seman.c roles
• Tim broke [ the laser pointer.]
• [ The windows] were broken by the
hurricane.
• [ The vase] broke into pieces when it
toppled over.
Breake
r
Thing broken
Thing broken
7. A proposition as a tree
Zhu and Powell discussed the return of the spy plane
discuss([Powell, Zhu], return(X, plane))
Zhu and
Powell
of the
spy plane
discuss
return
10. discuss.01
ARG0: Zhu and Powell
ARG1: return.01
Arg1: of the spy plane
Zhu and Powell discussed the return of the spy plane
11. discuss.01
ARG0: Zhu and Powell
ARG1: return.01
Arg1: of the spy plane
discuss([Powell, Zhu], return(X, plane))
Zhu and Powell discussed the return of the spy plane
12. A proposi,on as a tree
Zhu and Powell discussed the return of the spy plane
discuss([Powell, Zhu], return(X, plane))
Zhu and
Powell
of the
spy plane
discuss.01
return.02
Arg0 Arg1
Arg1
13. A proposition as a tree
Zhu and Powell discussed the return of the spy plane
discuss([Powell, Zhu], return(X, plane))
Zhu and
Powell
of the
spy plane
discuss.01
return.02
Arg0 Arg1
Arg1
Arg0
14. A proposition as a tree
Zhu and Powell discussed the return of the spy plane
discuss([Powell, Zhu], return(X, plane))
Zhu and
Powell
of the
spy plane
discuss.01
return.02
Arg0 Arg1
Arg1
Arg0
?? (Zhu)
15. A proposi,on as a tree
Zhu and Powell discussed the return of the spy plane
discuss([Powell, Zhu], return(X, plane))
Zhu and
Powell
of the
spy plane
discuss.01
return.02
Arg0 Arg1
Arg1
16. Proposi.on Bank
• Hand annotated predicate argument structures for Penn Treebank
• Standoff XML, points directly to syntac=c parse tree nodes, 1M words
• Doubly annotated and adjudicated
• (Kingsbury & Palmer, 2002, Palmer, Gildea, Xue, 2004, …).
• Based on PropBank Frame Files
• English valency lexicon: ~4K verb entries (2004) → ~11K v,n, adj, prep (2022)
• Core arguments – Arg0-Arg5
• ArgM’s for modifiers and adjuncts
• Mappings to VerbNet and FrameNet
• Annotated PropBank Corpora
• English 2M+, Chinese 1M+, Arabic .5M, Hindi/Urdu .6K, Korean, …
17. An Abstract Meaning Representation as a graph
Zhu and Powell discussed the return of the spy plane
discuss([Powell, Zhu], return(X, plane))
Zhu and
Powell
of the
spy plane
discuss.01
return.02
Arg0 Arg1
Arg1
18. An Abstract Meaning Representation as a graph
Zhu and Powell discussed the return of the spy plane
discuss([Zhu, Powell], return(X, plane))
and
spy plane
discuss.01
return.02
Arg0 Arg1
Arg1
AMR drops:
Determiners
Function words
adds:
NE tags.
Wiki links
19. An Abstract Meaning Representation as a graph
Zhu and Powell discussed the return of the spy plane
discuss([Zhu, Powell], return(X, plane))
and
plane
discuss.01
return.02
Arg0 Arg1
Arg1
AMR drops:
Determiners
Function words
adds:
NE tags.
Wiki links
Noun Phrase Structure
spy.01
Arg0-of
20. An Abstract Meaning Representa,on as a graph
Zhu and Powell discussed the return of the spy plane
discuss([Powell, Zhu], return(X, plane))
and
plane
discuss.01
return.02
Arg0 Arg1
Arg1
Arg0
?? (Zhu)
AMR drops:
Determiners
Function words
adds:
NE tags.
Wiki links
Noun Phrase Structure
Implicit Arguments
Coreference Links
spy.01
Arg0-of
21. An Abstract Meaning Representa,on as a graph
Zhu and Powell discussed the return of the spy plane
discuss([Powell, Zhu], return(X, plane))
and
of the
spy plane
discuss.01
return.02
Arg0 Arg1
Arg1
Arg0
?? (Zhu)
AMR drops:
Determiners
Function words
adds:
NE tags.
Wiki links
Noun Phrase Structure
Implicit Arguments
Coreference Links
spy.01
Arg0-of
23. Mo#va#on: From Sentences to Proposi/ons
Who did what to whom, when, where and how?
Powell met Zhu Rongji
Proposition: meet(Powell, Zhu Rongji)
Powell met with Zhu Rongji
Powell and Zhu Rongji met
Powell and Zhu Rongji had
a meeting
. . .
When Powell met Zhu Rongji on Thursday they discussed the return of the spy plane.
meet(Powell, Zhu) discuss([Powell, Zhu], return(X, plane))
debate
consult
join
wrestle
battle
meet(Somebody1, Somebody2)
24. Motivation: From Sentences to Propositions
Who did what to whom, when, where and how?
Powell met Zhu Rongji
Proposition: meet(Powell, Zhu Rongji)
Powell met with Zhu Rongji
Powell and Zhu Rongji met
Powell and Zhu Rongji had
a meeting
. . .
When Powell met Zhu Rongji on Thursday they discussed the return of the spy plane.
meet(Powell, Zhu) discuss([Powell, Zhu], return(X, plane))
debate
consult
join
wrestle
battle
meet(Somebody1, Somebody2)
ENGLISH!
25. Mo#va#on: From Sentences to Proposi/ons
Who did what to whom, when, where and how?
Powell reunió Zhu Rongji
Proposition: reunir(Powell, Zhu Rongji)
Powell reunió con Zhu Rongji
Powell y Zhu Rongji reunió
Powell y Zhu Rongji
tuvo una reunión
. . .
Powell se reunió con Zhu Rongji el jueves y hablaron sobre el regreso del avión espía.
reunir(Powell, Zhu) hablar[Powell, Zhu], regresar(X, avión))
зустрів
ا
ﻟ
ﺘ
ﻘ
ﻰ
遇⻅
मुलाकात की
พบ
meet(Somebody1, Somebody2)
Thai
Hindi
Chinese
Ukrainian
Arabic
Other
Languages?
Spanish
26. • Several languages already have valency lexicons
• Chinese, Arabic, Hindi/Urdu, Korean PropBanks, ….
• Czech Tectogrammatical SynSemClass , https://ufal.mff.cuni.cz/synsemclass
• VerbNets, FrameNets: Spanish, Basque, Catalan, Portuguese, Japanese, …
• Linguistic valency lexicons: Arapaho, Lakota, Turkish, Farsi, Japanese, …
• For those without, follow EuroWordNet approach: project from English?
• Universal Proposition Banks for Multilingual Semantic Role Labeling
• See Ishan Jindal in Part 2
• Can AMR be applied universally to build language specific AMRs?
• Uniform Meaning Representation
• See Nianwen Xue after the AM break
How do we cover thousands of languages?
27. • Universal PropBank was developed by IBM, primarily with translaLon
Prac=cal and efficient, produces consistent representa=ons for all languages
Projects English frames to parallel sentences in 23 languages
• BUT - May obscure language specific seman=c nuances
Not op=mal for target language applica=ons: IE, QA,…
• Uniform Meaning RepresentaLon
• Richer than PropBank alone
• Captures language specific characteris=cs while preserving
• consistency
• BUT - Producing sufficient hand annotated data is SLOW!
• Comparisons of UP/UMR will teach us a lot about
differences between languages
UP vs UMR
28. • Morning Session, Part 1
• Introduc=on - Martha Palmer
• Background and Resources – Martha Palmer
• Abstract Meaning Representa=ons - Tim O’Gorman
• Break
• Morning Session, Part 2
• Rela=ons to other Meaning Formalisms: AMR, UCCA, Tectogramma=cal, DRS (Parallel
Meaning Bank), Minimal Recursion Seman=cs and Seman=c Parsing – Tim O’Gorman
• Uniform Meaning Representa=ons – Nianwen Xue
Tutorial Outline
29. • Afternoon Session, Part 1
• Modeling Meaning Representation: SRL - Ishan Jindal
• Modeling Meaning Representation: AMR – Jeff Flanigan
• Break
• Afternoon Session, Part 2
• Applying Meaning Representations – Yunyao Li, Jeff Flanigan
• Open Questions and Future Work – Tim O’Gorman
Tutorial Outline
30. Meaning Representations for Natural Languages Tutorial Part 2
Common Meaning Representations
Jeffrey Flanigan, Tim O’Gorman, Ishan Jindal, Yunyao Li, Martha Palmer, Nianwen Xue
31. • AMR as a format is older (Kasper 1989,
Langkilde & Knight 1998), but with no
PropBank, no training data.
• Propbank showed that large-scale training
sets could be annotated for SRL
• Modern AMR (Banarescu et al. (2013)
main innovation: making large-scale
sembanking possible:
• AMR 3.0 more than 60k sentences in English
• CAMR more than 20k sentences in Chinese
“AMR” annota,on
32. • Shi$ from SRL to AMR – from spans
to graphs
• In SRL we separately represent each
predicate’s arguments with spans
• AMR instead uses graphs with one
node per concept
AMR Basics – SRL to AMR
33. • “PENMAN” is the text-based format
used to represent these graphs
AMR Basics – PENMAN
(l / like-01
:ARG0 (c / cat
:mod (l / little))
:ARG1 (e / eat-01
:ARG0 c
:ARG1 (c2 / cheese)))
34. • Edges are represented by
indentation and colons (:EDGE)
• Individual variables identify each
node
AMR Basics – PENMAN
(l / like-01
:ARG0 (c / cat
:mod (l / little))
:ARG1 (e / eat-01
:ARG0 c
:ARG1 (c2 / cheese)))
35. • If a node has more than one edge, it
can be referred to again using that
variable.
• Terminology: We call that a re-
entrancy
• This is used for all references to the
same enPty/thing in a sentence!
• This is what allows us to encode
graphs in this tree-like format
AMR Basics – PENMAN
(l / like-01
:ARG0 (c / cat
:mod (l / little))
:ARG1 (e / eat-01
:ARG0 c
:ARG1 (c2 / cheese)))
36. • Inverse roles allow us to encode
things like relative clauses
• Any relation of the form “:X-of” is
an inverse.
• Interchangeable!
• (entity, ARG0-of, predicate)
generally equal to
(predicate, ARG0, entity)
AMR Basics – PENMAN
(l / like-01
:ARG0 (h / he)
:ARG1 (c / cat
:ARG0-of (e / eat-01
:ARG1 (c2 / cheese))))
37. • Are the graphs the same for “cats that eat cheese” and “cats eat
cheese”?
• No! Every graph gets a “Top” edge defining the semantic head/root
AMR Basics – PENMAN
(c / cat
:ARG0-of (e / eat-01
:ARG1 (c2 / cheese)))
(e / eat-01
:ARG0 (c / cat)
:ARG1 (c2 / cheese))
38. • Named en))es are typed and then linked to a
“name” node with features for each name token.
• 70+ categories like person, government-organiza)on,
newspaper, city, food-dish, conference
• Note that name strings (and some other things like
numbers) are constants — they aren’t assigned
variables.
• En)ty linking: connect to wikipedia entry for each NE
(when available)
AMR Basics – PENMAN
39. • That’s AMR notation! Let’s review before discussing how
we annotate AMRs.
(e / eat-01
:ARG0 (d / dog)
:ARG1 (b / bone :quant 4
:ARG1-of (f / find-01
:ARG0 d)))
3
9
variable concept constant
inverse rela>on reentrancy
AMR Basics – PENMAN
40. • AMR does limited normalization aimed at reducing arbitrary
syntactic variation (“syntactic sugar”) and maximizing cross-
linguistic robustness
• Mapping all predicative things (verbs, adjectives, many nouns)
to PropBank predicates. Some morphological decomposition
• Limited speculation: mostly represent direct contents of
sentence (add pragmatic content only when it can be done
consistently)
• Canonicalize the rest: removal of semantically light predicates
and some features like definiteness (controversial)
AMR Basics 2 – Annotation Philosophy
41. AMR Basics 2 – Annotation Philosophy
• We generalize across parts of speech and
etymologically related words:
• But we don’t generalize over synonyms (hard
to do consistently):
4
1
My fear of snakes fear-01
I’m terrified of snakes terrify-01
Snakes creep me out creep_out-03
My fear of snakes fear-01
I am fearful of snakes fear-01
I fear snakes fear-01
I’m afraid of snakes fear-01
42. AMR Basics 2 – Annotation Philosophy
• Predicates use the
PropBank inventory.
• Each frame presents
annotators with a list of
senses.
• Each sense has
its own definitions for its
numbered (core)
arguments
4
2
43. AMR Basics 2 – Annotation Philosophy
• If a seman)c role is not in
the core roles for a roleset,
AMR provides an inventory
of non-core roles
• These express things like
:+me, :manner, :part,
:loca+on, :frequency
• Inventory on handout, or in
editor (the [roles] bu@on)
4
3
44. AMR Basics 2 – Annota4on Philosophy
• Ideally one seman)c
concept = one node
• Mul)-word predicates
modeled as a single node
• Complex words can be
decomposed
• Only limited, replicable
decomposi)on (e.g. kill
does not become “cause to
die”)
4
4
The thief was lining his pockets with
their investments
(l / line-pocket-02
:ARG0 (p / person
:ARG0-of (t / thieve-01))
:ARG1 (t2 / thing
:ARG2-of (i2 / invest-01
:ARG0 (t3 / they))))
45. AMR Basics 2 – Annotation Philosophy
• All concepts drop plurality, aspect,
definiteness, and tense.
• Non-predicative terms simply represented in
singular, nominative form
4
5
A cat
The cat
cats
the cats
(c / cat)
ea=ng
eats
ate
will eat
(e / eat-01)
They
Their
Them
(t / they)
46. 4
6
The man described the mission as a disaster.
The man’s description of the mission: disaster.
As the man described it, the mission was a disaster.
The man described the mission as disastrous.
(d / describe-01
:ARG0 (m / man)
:ARG1 (m2 / mission)
:ARG2 (d / disaster))
AMR Basics 2 – Annotation Philosophy
47. Meaning Representa=ons for Natural Languages Tutorial Part 2
Common Meaning Representa0ons
• Format & Basics
• Some Details & Design Decisions
• Prac=ce - Walking through a few AMRs
• Mul=-sentence AMRs
• Rela=on to Other Formalisms
• UMRs
• Open Ques=ons in Representa=on
Representa)on Roadmap
48. Details- Specialized Normaliza3ons
• We also have special entity types we use for
normalizable entities.
4
8
(d / date-entity
:weekday (t / tuesday)
:day 19)
(m / monetary-quantity
:unit dollar
:quant 5)
“Tuesday the 19th” “five bucks”
49. Details- Specialized Normaliza3ons
• We also have special enLty types we use for
normalizable enMMes.
4
9
(r / rate-entity-91
:ARG1 (m / monetary-quantity
:unit dollar
:quant 3)
:ARG2 (v / volume-quantity
:unit gallon
:quant 1))
“$3 / gallon”
50. Details - Specialized Predicates
• Common construcLons for kinship and
organizaLonal relaLons are given general
predicates like have-org-role-91
5
0
(p / person
:ARG0-of (h / have-org-role-91
:ARG1 (c / country
:name (n / name :op1 "US")
:wiki "United_States")
:ARG2 (p2 / president)
“The US president”
have-org-role-91
ARG0: office holder
ARG1: organization
ARG2: title of office held
ARG3: description of responsibility
51. Details - Specialized Predicates
• Common constructions for kinship and
organizational relations are given general
predicates like have-org-role-91
5
1
(p / person
:ARG0-of (h / have-rel-role-91
:ARG1 (s / she)
:ARG2 (f / father)
“Her father”
have-rel-role-91
ARG0: entity A
ARG1: entity B
ARG2: role of entity A
ARG3: role of entity B
ARG4: relationship basis
52. Coreference and Control
5
2
• Within sentences, all references to the same “referent” are merged
into the same variable.
• This applies even with pronouns or even descriptions
Pat saw a moose and she ran
(a / and
:op1 (s / see-01
:ARG0 (p /person
:name (n / name :op1 “Pat”))
:ARG1 (m / moose) )
:op2 (run-02
:ARG0 p))
53. Reduc)on of Seman)cally Light Matrix Verbs
5
3
• Specific predicates (specifically
the English copula) NOT used in
AMR.
• Copular predicates which
*many languages would omit*
are good candidates for
removal
• Replace with rela=ve
SEMANTIC asser=ons (e.g.
:domain is “is an atribute of”)
• UMR will discuss alterna=ves to
just omiung these.
the pizza is free
(f / free-01
:arg1 (p / pizza))
The house is a pit
(p / pit
:domain (h / house))
54. • For two-place discourse connectives, we
define frames
• Although it rained, we walked home
• For list-like things (including coordination) we
use “:op#” to define places in the list:
• Apples and bananas
5
4
(a / and
:op1 (a2 / apple)
:op2 (b / banana))
Have-concession-91:
Arg2: “although” clause
Arg1: main clause
Discourse Connec)ves and Coordina)on
55. Meaning Representations for Natural Languages Tutorial Part 2
Common Meaning Representations
• Format & Basics
• Some Details & Design Decisions
• Practice - Walking through a few AMRs
• Multi-sentence AMRs
• Relation to Other Formalisms
• UMRs
• Open Questions in Representation
Representation Roadmap
56. Practice - Let’s Try some Sentences
• Feel free to annotate by hand (or ponder how you’d want to represent them)
• Edmund Pope tasted freedom today for the first 3me in more than eight months.
• Pope is the American businessman who was convicted last week on spying charges and sentenced to
20 years in a Russian prison.
Taste-01:
Arg0: taster
Arg1: food
Useful Normalized forms:
- Rate-en5ty
- Ordinal-en5ty
- Date-en5ty
- Temporal-quan5ty
Useful NER types:
- Person
- Country
Convict-01
Arg0: judge
Arg1: person convicted
Arg2: convicted of what
Spy-01
Arg0: secret agent
Arg1: entity spied /seen
Charge-01
Asking price
Arg0: seller
Arg1: asking price
Arg2: buyer
Arg3 :commodity
Charge-05
Assign a role
(including criminal charges)
Arg0:assigner
Arg1 : assignee
Arg2: role or crime
Sentence-01
Arg0: judge/jury
Arg1: criminal
Arg2: punishment
57. Prac3ce- Let’s Try some Sentences
Edmund Pope tasted freedom today for the first time in more than eight months.
(t2 / taste-01
:ARG0 (p / person :wiki "Edmond_Pope"
:name (n2 / name :op1 "Edmund" :op2 "Pope"))
:ARG1 (f / free-04
:ARG1 p)
:time (t3 / today)
:ord (o3 / ordinal-entity :value 1
:range (m / more-than
:op1 (t / temporal-quantity :quant 8
:unit (m2 / month)))))
58. Prac3ce- Let’s Try some Sentences
Pope is the American businessman who was convicted last week
on spying charges and sentenced to 20 years in a Russian prison.
(b2 / businessman
:mod (c5 / country :wiki "United_States"
:name (n6 / name :op1 "America"))
:domain (p / person :wiki "Edmond_Pope"
:name (n5 / name :op1 "Pope"))
:ARG1-of (c4 / convict-01
:ARG2 (c / charge-05
:ARG1 b2
:ARG2 (s2 / spy-01
:ARG0 p))
:time (w / week
:mod (l / last)))
:ARG1-of (s / sentence-01
:ARG2 (p2 / prison
:mod (c3 / country :wiki "Russia"
:name (n4 / name :op1 "Russia"))
:duration (t3 / temporal-quantity :quant 20
:unit (y2 / year)))
:ARG3 s2))
59. Meaning Representations for Natural Languages Tutorial Part 2
Common Meaning Representations
• Format & Basics
• Some Details & Design Decisions
• Practice - Walking through a few AMRs
• Multi-sentence AMRs
• Relation to Other Formalisms
• UMRs
• Open Questions in Representation
Representation Roadmap
60. A final component in AMR: Multi-sentence!
• AMR 3.0 release contains Mul--sentence AMR annota-ons
• Document-level coreference:
• Connec=ng men=ons that co-refer
• Connec=ng some par=al coreference
• Making cross-sentence implicit seman=c roles
• John took his car to the store.
• He bought milk (from the store).
• He put it in the trunk.
61. A final component in AMR: Mul)-sentence!
• AMR 3.0 release contains Mul--sentence AMR annota-ons
• Annota=on was done between AMR variables, not raw text — nodes are coreferent
• (t / take-01
:ARG0 (p / person :name (n / name :op1 “John”))
:ARG1 (c / car :poss p)
:ARG3 (s / store)
• (B / buy-01
:ARG0 (h / he)
:ARG1 (m / milk))
62. A final component in AMR: Mul)-sentence!
• AMR 3.0 release contains Multi-sentence AMR annotations
• "implicit role" annotation was done by showing the remaining roles to annotators
and allowing them to be added to coreference chains.
• (t / take-01
:ARG0 (p / person :name (n / name :op1 “John”))
:ARG1 (c / car :poss p)
• :ARG2 (x / implicit :op1 “taken from, source…”
:ARG3 (s / store)
• (B / buy-01
:ARG0 (h / he)
:ARG1 (m / milk)
:ARG2 (x / implicit :op1“seller”)
63. A final component in AMR: Multi-sentence!
• AMR 3.0 release contains Multi-sentence AMR annotations
• Implicit roles are worth considering for meaning representation, especially for
languages other than English
• Null subject (and sometimes null object) constructions are very cross-linguistically
common, can carry lots of information
• Arguments of nominalizations can carry a lot of assumed information in scientific
domains
64. A final component in AMR: Multi-sentence!
• MulL-sentence AMR data: training and evaluaLon data for creaLng a graph for
a whole document
• Was not impossible before mul=-sentence AMR: could boostrap with span-based
coreference data
• Also extended to spa=al AMRs (human-robot interac=ons - Bonn et al .2022
• MS-AMR work was done on top of exisLng gold AMR annotaLons — a separate
process.
65. Meaning Representa=ons for Natural Languages Tutorial Part 2
Common Meaning Representa0ons
• Format & Basics
• Some Details & Design Decisions
• Prac=ce - Walking through a few AMRs
• Mul=-sentence AMRs
• Rela>on to Other Formalisms
• UMRs
• Open Ques=ons in Representa=on
Representa6on Roadmap
66. Comparison to Other Frameworks
6
6
• Meaning representations vary along many
dimensions!
• How meaning is connected to text
• Relationship to logical and/or executable form
• Mapping to Lexicons/Ontologies/Tasks
• Relationship to discourse
• We’ll overview these followed by some side-
by-side comparisons
67. Alignment to Text / Compositionality
6
7
• Historical approach to meaning representa1ons: represent context-free seman1cs,
as defined by a par1cular grammar model
• AMR at other extreme: AMR graph annotated for a single sentence, but no
individual mapping from tokens to nodes
68. Alignment to Text / Composi6onality
6
8
Oepen & Kuhlmann (2016) “flavors” of meaning representations:
Type 0: Bilexical Type 1: Anchored Type 2: Unanchored
Nodes each correspond
to one token
(Dependency parsing)
Nodes are aligned to text
(can be subtoken or
multi-token)
No mapping from graph
to surface form
Universal Dependencies UCCA AMR
MRS-connected
frameworks (DM, EDS)
DRS-based frameworks
(PMB / GMB)
Some executable/task-
specific semantic parsing
frameworks
Prague Semantic
dependencies
Prague tectogrammatical
69. Alignment to Text / Compositionality
6
9
Less thoroughly defined: adherence to grammar/composiAonally (cf. Bender et al. 2015)
Some frameworks (MRS/ DRS below) have parAcular asserAons about how a given meaning representaAon was derived (Aed to a parAcular
grammar)
AMR encodes many useful things that are oPen *not* considered composiAonal — named enAty typing, cross-sentence coreference, word
senses, etc.
<- “Sentence meaning” Extragrammatical inference ->
Only encode “compositional”
meanings predicted by a
particular theory of grammar
some useful pragmatic
inference (e.g. sense
distinctions, named entity
types)
Any wild inferences needed for
task
70. Alignment to Text / Compositionality - UCCA
7
0
• Universal Conceptual Cogni2ve Annota2on : based on a typological
theory (Dixon’s BLT) of how to do coarse-grained seman2cs across
languages
• Similar to a cross between dependency and cons2tuency parses (labeled
edges)- some2mes very syntac2c
• Coarse-grained roles, e.g.:
• A: par2cipant
• S: State
• C: Center
• D: Adverbial
• E: elaborator
• “Anchored” graphs, in the Open & Kuhlman taxonomy (somewhat
composi2onal, but no formal rules for how a given node is derived)
71. Alignment to Text / Compositionality - Prague
7
1
• Very similar to AMR with more general semantic roles (predicates use
Vallex predicates (valency lexicon) and a shared set of semantic roles
similar to VerbNet)
• Semantic graph is aligned to syntactic graph layers (“type 1”)
• “Prague Czech-English Dependency Treebank”
• “PSD” reduced form fully bilexical (“Type 0”) for dependency
parsing.
• Full PCEDT also has rich semantics like implicit roles (e.g. null
subjects) – “anchored” (“Type 1”)
For the Czech version of “An earthquake struck
Northern California, killing more than 50
people.” (Čmejrek et al. 2004)
72. Logical & Executable Forms
7
2
• Lots of logical desiderata:
• Modeling whether events happen and/or are believed (and other modality
questions): Sam believes that Bill didn’t eat the plums.
• Understanding quantifications: whether “every child has a favorite song” refers
to one song or many
• Technically our default assumption for AMR is Neo-Davidsonian: bag of triples like
(“instance-of(b, believe-01)”, “instance-of(h, he), “ARG0(b, h)”
• One cannot modify more than one node in the graph
• PENMAN is a bracketed tree that can be treated like a logical form (with certain
assumptions or addition to certain new annotations)
• Artzi et al. 2015), Bos (2016), Stabler (2017), : Pustejovsky et al. (2019), etc.
• Competing frameworks like DRS and MRS more specialized for this.
73. Logical & Executable Forms
7
3
• Lots of logical desiderata:
• Modeling whether events happen and/or are believed (and other modality
questions): Sam believes that Bill didn’t eat the plums.
• Understanding quantifications: whether “every child has a favorite song” refers
to one song or many
• Technically our default assumption for AMR just means that something like “:polarity
-“ is a feature of a single node; no semantics for quantifiers like “every”
• With certain assumptions or addition to certain new annotations, PENMAN is a
bracketed tree that can be treated like a logical form
• Artzi et al. 2015), Bos (2016), Stabler (2017), : Pustejovsky et al. (2019), etc.;
proposals for “UMR” treatments as well.
• Competing frameworks like DRS and MRS more specialized for this.
74. Logical & Executable Forms - DRS
7
4
• Discourse Representa1on Structures (annota1ons in
Groening Meaning Bank and Parallel Meaning Bank)
• DRS frameworks do scoped meaning representa1on
• Outputs originally modified from CCG parser LF
outputs-> DRS
• DRS uses “boxes” which can be negated, asserted,
believed in.
• This is not na1vely a graph representa1on! “box
variables”(bo[om) one way of thinking about
these
• a triple like “agent(e1, x1)” is part of b3
• Box b3 is modified (e.g. b2 POS b3)
75. Logical & Executable Forms - DRS
7
5
• Grounded in long theore5cal DRS tradi5on (Heim &
Kamp) for handling discourse referents, presupposi/ons,
discourse connec/ves, temporal rela/ons across
sentences, etc.
• DRS for “everyone was killed” (Liu et al. 2021)
76. Logical & Executable Forms - MRS
7
6
Minimal Recursion Semantics (and related frameworks)
• Copestake (1997) model proposed for semantics of HPSG - this is
connected to other underspecification solutions (Glue semantics /
hole semantics / etc. )
• Define set of constraints over which variables outscope other
variables
• HPSG grammars like the English Resource Grammar produce ERS
(English resource semantics) outputs (which are roughly MRS) and
have been modified into a simplified DM format (“type 0” bilexical
dependency)
77. Logical & Executable Forms - MRS
7
7
• Underspecification in practice:
• MRS can the thought of as many fragments with constraints on
how they scope together
• Those define a set of MANY possible combinations
into a fully scoped output, e.g.:
Every dog barks and chases a cat(as interpreted in Manshadi et al. 2017)
78. Logical & Executable Forms- MRS
7
8
• Variables starting with h are “handle”
variables used to define constraints on
scope.
• h19 = things under scope of negation
• H21 = leave_v_1 head
• H19 =q h21 : equality modulo
quantifiers
• (Neg outscopes leave)
• “forest” of possible readings
• Takeaway: Constraints on which variables
“outscope" others can add flexible amounts
of scope info
79. Lexicon/Ontology Differences
7
9
• Predicates can use different ontologies – e.g. more grounded in
grammar/valency, or more tied to taxonomies like WordNet
• Semantic Roles can be encoded differently, e.g. with non-lexicalized
semantic roles (discussed for UMR later)
• Some additional proposals: “BabelNet Meaning Representation”
propose using VerbAtlas (clusters over wordnet senses with VerbNet
semantic role templates)
DRS (GMB/PMB) MRS Prague (PCEDT ) AMR UCCA
Semantic Roles VerbNet (general
roles)
General roles General roles +
valency lexicon
Lexicalized numbered
arguments
Fixed general roles
Predicates WordNet grammatical entries Vallex valency lexicon
(Propbank-like)
Propbank Predicates A few types (State vs
process …)
non-predicates wordnet Lemmas Lemmas Named entity types Lemmas
80. Task-specific Representations
8
0
• Many use “Seman1c Parsing” to refer to task-specific, executable
representa1ons
• Text-to-SQL
• interac1on with robots, text to code/commands
• interac1on with determinis1c systems like calendars/travel
planners
• Similar dis1nc1ons to a general-purpose meaning representa1on, BUT
• May need to map into specific task taxonomies and ignore
content not relevant to task
• Can require more detail or inference than what’s assumed for
“context-free” representa1ons
• Ogen can be thought of as first-order logic forms — simple
predicates + scope
82. Task-specific Representa6ons- Spa6al AMR
8
2
• Additional example of task-specific semantic parsing is human-robot
interaction
• Non-trivial to simply pull those interactions from AMR: normal human
language is not normally sufficiently informative about spatial positioning,
frames of reference, etc.
• Spatial AMR project (Bonn et al. 2020) a good example of project
attempting to add all “additional detail” needed to handle structure-
building dialogues (giving instructions for building Minecraft structures)
• Released with dataset of building actions, success/failures, views
of the event different angles.
83. Discourse-Level Annotation
8
3
• Do you do multi-sentence coreference?
• Partial coreference (set-subset, implicit roles,
etc.)?
• Discourse connectives?
• Treatment of multi-sentence tense, modality,
etc.?
• Prague Tectogrammatical annotations & AMR
only general-purpose representations with
extensive multi-sentence annotations
84. Overviewing Frameworks vs. AMR
Alignment Logical Scoping &
Interpretation
Ontologies and
Task-Specifc
Discourse-Level
DRS (Groeningen /
Parallel)
Compositional
/Anchored
Scoped
representation
(boxes)
Rich predicates
(WordNet), general
roles
Can handle
referents,
connectives
MRS Compositional
/Anchored
Underspecified
scoped
representation
Simple predicates,
general roles
N/a
UCCA Anchored Not really scoped Simple predicates,
general roles
Some implicit roles
Prague Tecto Anchored Not really scoped Rich predicates,
semi-lexicalizekd
roles
Rich multi-
sentence
conference
AMR Unanchored
(English);
Anchored
(Chinese)
Not really scoped
yet
Rich predicates,
lexicalized roles
Rich multi-
sentence
conference
85. End of Meaning Representation Comparison
• What’s next: UMR — proposal within AMR-connected
scholars on next steps for AMR.
• QuesHons about how AMR is annotated?
• QuesHons about how it relates to other meaning
representaHon formalisms?
86. Meaning Representations for Natural Languages Tutorial Part 2
Common Meaning Representations
Jeffrey Flanigan, Tim O’Gorman, Ishan Jindal, Yunyao Li, Martha Palmer, Nianwen Xue
87. Outline
► Background
► Do we need a new meaning representation? What’s wrong with existing
meaning representations?
► Aspects of Uniform Meaning Representation (UMR)
► UMR starts with AMR but made a number of enrichments
► UMR is a document-level meaning representation that represents temporal
dependencies, modal dependencies, and coreference
► UMR is a cross-lingual meaning representation that
separates aspects of meaning that are shared across languages
language-independent from those that are idiosyncratic to individual
languages (language-specific)
► UMR-Writer -- a tool for annotating UMRs
88. Why aren’t exisHng meaning representaHons sufficient?
► Existing meaning representations vary a great deal in their focus
and perspective
► Formal semantic representations aimed at supporting logical inference
focus on the proper representation of quantification, negation, tense,
and modality (e.g., Minimal Recursion Semantics (MRS) and Discourse
Representation Theory (DRT).
► Lexical semantic representations focus on the proper representation of
core predicate-argument structures, word sense, named entities and
relations between them, coreference (e.g., Tectogrammatical
Representation (TR), AMR).
► The semantic ontology they use also differ a great deal. For
example, MRS doesn’t have a classification of named entities at
all, while AMR has over 100 types of named entities
89. UMR uses AMR as a starting point
► Our starting point is AMR, which has a number of
attractive properties:
► Easy to read,
► scalable (can be directly annotated without relying on syntactic
structures),
► has information that is important to downstream applications (e.g.,
semantic roles, named entities and coreference),
► represented in a well-defined mathematical structure (asingle-rooted,
directed, acylical graph)
► Our general strategy is to augment AMR with meaning
components that are missing and adapt it to cross-lingual
settings
90. ParHcipants of the UMR project
► UMR stands for Uniform Meaning Representation, and it is an
NSF funded collaborative project between Brandeis University,
University of Colorado, and University of New Mexico, with a
number of partners outside these institions
91. From AMR to UMR Gysel et al. (2021)
► At the sentence level, UMR adds:
► An aspect attribute to eventive concepts
► Person and number attributes for pronouns and other nominal
expressions
► Quantification scope between quantified expressions
► At the document level UMR adds:
► Temporal dependencies in lieu of tense
► Modal dependencies in lieu of modality
► Coreference relations beyond sentence boundaries
► To make UMR cross-linguistically applicable, UMR
► defines a set of language-independent abstract concepts and
participant roles,
► uses lattices to accommodate linguistic variability
► designs specifications for complicated mappings between words and
UMR concepts.
92. UMR sentence-level addi6ons
► An Aspect attribute to event concepts
► Aspect refers to the internal constituency of events - their
temporal and qualitative boundedness
► Person and number attributes for pronouns and other
nominal expressions
► A set of concepts and relations for discourse relations
between clauses
► Quantification scope between quantified expressions to
facilitate translation of UMR to logical expressions
94. UMR aNribute: coarse-grained aspect
► State: unspecified type of state
► Habitual: an event that occurs regularly in the
past or present, including generic statements
► Activity: an event that has not necessarily ended and
may be ongoing at Document Creation Time (DCT).
► Endeavor: a process that ends without reaching
completion (i.e., termination)
► Performance: a process that reaches a completed
result
state
95. Coarse-grained Aspect as an UMR attribute
He wants to travel to Albuquerque.
(w / want
:aspect State)
She rides her bike to
work.
(r / ride
:aspect Habitual)
He was writing his
paper yesterday.
(w / write
:aspect Activity)
Mary mowed the lawn for thirty
minutes.
(m / mow
:aspect Endeavor)
96. Fine-grained Aspect as an UMR attribute
My cat is hungry.
(h / have-mod-91
:aspect Reversible state)
The wine glass is
shattered.
(h / have-mod-91
:aspect Irreversible state)
My cat is black and white.
(h / have-mod-91
:aspect Inherent state)
It is 2:30pm.
(h / have-mod-91
:aspect Point state)
97. AMR vs UMR on how pronouns are represented
► In AMR, pronouns are treated as unanalyzable concepts
► However, pronouns differ from language to language, so UMR
decomposes them into person and number attributes
► These attributes can be applied to nominal expressions too
AMR:
(s / see-01
:ARG0 (h/ he)
:ARG1 (b/ bird
:mod (r/ rare)))
UMR:
(s / see-01
:ARG0 (p / person
:ref-person 3rd
:ref-number Sing.)
:ARG1 (b / bird
:mod (r/ rare)
:ref-number Plural))
“He saw rare birds
today.”
100. Discourse relations in UMR
► In AMR, there is a minimal system for indicating
relationships between clauses - specifically coordination:
► and concept and :opX relations for addition
► or/either/neither concepts and :opX relations for disjunction
► contrast-01 and its participant roles for contrast
► Many subordinated relationships are represented through
participant roles, e.g.:
► :manner
► :purpose
► :condition
► UMR makes explicit the semantic relations between (more
general) “coordination” semantics and (more specific)
“subordination” semantics
101. Discourse relations in UMR
Discours
e
Relations
inclusive-disj
or
and + but
exclusive-disj
and +
unexpected
and +
contrast
but-91
and
consecutive
additive
unexpected-co-
occurrence-91
contrast-91
:apprehensive
:condition
:cause
:purpose
:temporal
:manner
:pure-addition
:substitute
:concession
:concessive-
condition
:subtraction
102. Disambiguation of quantification scope in UMR
“Someone didn’t answer all the questions”
(a / answer-01
:ARG0 (p / person)
:ARG1 (q / question :quant All :polarity -)
:pred-of (s / scope :ARG0 p :ARG1 q))
∃p(person(p) ∧ ¬∀q(question(q) →
∃a(answer-01(a) ∧ ARG1(a, q) ∧ ARG0(a, p))))
103. Quantification scope annotation
► Scope will not be annotated for summation readings, nor is
it annotated where a distributive or collective reading can be
predictably derived from the lexical semantics.
► The linguistics students ran 5 kilometers to raise money for charity.
► The linguistics students carried a piano into the theater.
► Ten hurricanes hit six states over the weekend.
► The scope annotation only comes into play when some
overt linguistic element forces an interpretation that
diverges from the lexical default
► The linguistics students together ran 200 kilometers to raise
money for charity.
► The bodybuilders each carried a piano into the theater.
► Ten hurricanes each hit six states over the weekend.
104. From AMR to UMR Gysel et al. (2021)
► At the sentence level, UMR adds:
► An aspect attribute to eventive concepts
► Person and number attributes for pronouns and other nominal
expressions
► Quantification scope between quantified expressions
► At the document level UMR adds:
► Temporal dependencies in lieu of tense
► Modal dependencies in lieu of modality
► Coreference relations beyond sentence boundaries
► To make UMR cross-linguistically applicable, UMR
► defines a set of language-independent abstract concepts and
participant roles,
► uses lattices to accommodate linguistic variability
► designs specifications for complicated mappings between words and
UMR concepts.
105. UMR is a document-level representation
► Temporal relations are added to UMR graphs as
temporal dependencies
► Modal relations are also added to UMR graphs as
modal dependencies
► Coreference is added to UMR graphs as identity or
subset relations between named entities or events
106. No representation of tense in AMR
talk-01
she
he
ARG0
ARG2
medium
language
name
name
op1
“French”
(t / talk-01
:ARG0 (s / she)
:ARG2 (h / he)
:medium (l / language
:name (n / name
:op1 "French")))
► “She talked to him in French.”
► “She is talking to him in French.”
► “She will talk to him in French.”
107. Adding tense seems straighMorward...
Adding tense to AMR involves defining a temporal relation
between event-time and the Document Creation Time
(DCT) or speech time (Donatelli et al 2019).
talk-01
she
he
ARG0
ARG2
medium
time
before
op1
now
language
name
name
op1
“French”
(t / talk-01
:time (b / before
:op1 (n / now)))
:ARG0 (s / she)
:ARG2 (h / he)
:medium (l / language
:name (n / name
:op1 "French")))
“She talked to him in French.”
108. ... but it isn’t
► For some events, its temporal relation to the DCT or
speech time is undefined. “John said he would go to the
florist shop”.
► Is “going to the florist shop” before or after the DCT?
► Its temporal relation is more naturally defined with respect to “said”.
► In quoted speech, the speech time has shifted. “I visited my
aunt on the weekend,” Tom said.
► The reference time for “visited” has shifted to the time when
Tom said this. We only know the “visiting” event happened
before the DCT indirectly.
► Tense is not universally grammaticalized, e.g., Chinese
109. Limita9ons of simply adding tense
► Even in cases when tense, i.e., the temporal relation between an event
and the DCT is clear, tense may not give us the most precise temporal
location of the event.
► John went into the florist shop.
► He had promised Mary some flowers.
► He picked out three red roses, two white ones and one pale pink
► Example from (Webber 1988)
► All three events happened before the DCT, but we also know that the
“going” event happened after the “promising” event, but before the
“picking out” event.
110. UMR represents temporal relations in a document as
temporal dependency structures (TDS)
► The temporal dependency structure annotation involves
identifying the most specific reference time for each event
► Time expressions and other events are normally the most
specific reference times
► In some cases, an event may require two reference times in
order to make its temporal location as specific as possible
Zhang and Xue (2018); Yao et al. (2020)
111. TDS Annotation
► If an event is not clearly linked temporally to either a
time expression or another event, then it can be linked
to the DCT or tense metanodes
► Tense metanodes capture vague stretches of time that
correspond to grammatical tense
► Past_Ref, Present_Ref, Future_Ref
► DCT is a more specific reference time than a tense
metanode
112. Temporal dependency Structure (TDS)
► If we identify a reference time for every event and time
expression in a document, the result will be a
Temporal Dependency Graph.
descended
arrested
assaulted
ROOT
Temporal
DCT (4/30/2020
Depends-on
today
Contained
Contained
Contained
After Before
“700 people descended on the state Capitol today, according
to Michigan State Police. State Police made one arrest, where
one protester had assaulted another, Lt. Brian Oleksyk said.”
113. Genre in TDS Annotation
► Temporal relations function differently depending on the
genre of the text (e.g., Smith 2003)
► Certain genres proceed in temporal sequence from one
clause to the next
► While other genres involve generally non-sequenced
events
► News stories are a special type
► many events are temporally sequenced
► temporal sequence does not match with sequencing in the text
114. TDS Annotation
► Annotators may also consider the modal annotation when
annotating temporal relations
► Events in the same modal “world” can be temporally linked to
each other
► Events in non-real mental spaces rarely make good
reference times for events in the “real world”
► Joe got to the restaurant, but his friends had not arrived. So, he
sat down and ordered a drink.
► Exception to this are deontic complement-taking
predicates
► Events in the complement are temporally linked to the
complement-taking predicate
► E.g. I want to travel to France: After (want, travel)
115. Modality in AMR
► Modality characterizes the reality status of events, without
which the meaning representation of a text is incomplete
► AMR has six concepts that represent modality:
► possible-01, e.g., “The boy can go.”
► obligate-01, e.g., “The boy must go.”
► permit-01, e.g., “The boy may go.”
► recommend-01, e.g., “The boy should go.”
► likely-01, e.g., “The boy is likely to go.”
► prefer-01, e.g., “They boy would rather go.”
► Modality in AMR is represented as senses of an English
verb or adjective.
► However, the same exact concepts for modality may not
apply to other languages
116. Modal dependency structure
► Modality is represented as a dependency structure in
UMR
► Similar to the temporal relations
► Events and conceivers (sources) are nodes in
the dependency structure
► Modal strength and polarity values characterize the edges
► Mary might be walking the dog.
AUTH
Neutral
walk
117. Modal dependency structure
► A dependency structure:
► Allows for the nesting of modal operators (scope)
► Allows for the annotation of scope relations between
modality and negation
► Allows for the import of theoretical insights from Mental
Space Theory (Fauconnier 1994, 1997)
118. Modal dependency structure
► There are two types of nodes in the modal
dependency structure: events and conceivers
► Conceivers
► Mental-level entities whose perspective is modelled in
the text
► Each text has an author node (or nodes)
► All other conceivers are children of the AUTH node
► Conceivers may be nested under other conceivers
► Mary said that Henry wants...
AUTH MARY HENRY
120. Modal dependency structure (MDS)
Michigan State Police
descended
arrested assaulted
ROOT
MODAL
AUTH (CNN)
FULLAFF FULLAFF
FULLAFF
Lt. Brian Oleksyk
FULLAFF FULLAFF
“700 people descended on the state Capitol today, according to
Michigan State Police. State Police made one arrest, where one
protester had assaulted another, Lt. Brian Oleksyk said.”
(Vigus et al., 2019; Yao et al., 2021):
121. En9ty Coreference in UMR
► same-entity:
1. Edmund Pope tasted freedom today for the first time
in more than eight months.
2. He denied any wrongdoing.
► subset:
1. He is very possesive and controlling but he has no right
to be as we are not together.
122. Event coreference in UMR
► same-event
1. El-Shater and Malek’s property was confiscated and is believed to
be worth millions of dollars.
2. Abdel-Maksoud stated the confiscation will affect the Brotherhood’s
financial bases.
► same-event
1. The Three Gorges project on the Yangtze River has recently introduced
the first foreign capital.
2. The loan , a sum of 12.5 million US dollars , is an export credit
provided to the Three Gorges project by the Canadian government ,
which will be used mainly for the management system of the Three
Gorges project .
► subset:
1. 1 arrest took place in the Netherlands and another in Germany.
2. The arrests were ordered by anti-terrorism judge fragnoli.
123. An UMR example with coreference
He is controlling but he has no right to be as we are not together.
(s4c / but-91
:ARG1 (s4c3 / control-01
:ARG0 (s4p2 / person
:ref-person 3rd
:ref-number Singular))
:ARG2 (s4r / right-05
:ARG1 s4p2
:ARG1-of (s4c2 / cause-01
:ARG0 (s4h / have-mod-91
:ARG0 (s4p3 / person
:ref-person 1st
:ref-number Plural)
:ARG1 (s4t/ together)
:aspect State
:modstr FullNeg))
:modstr FullNeg))
(s / sentence
:coref ((s4p2 :subset-of s4p3)))
124. Implicit
arguments
► Like MS-AMRs, UMR also annotates implicit arguments when they can
be inferred from context and can be annotated for coreference like
overt (pronominal) expressions
(s3d / deny-01
:Aspect Performance
:ARG0 (s3p / person
:ref-number Singular
:ref-person 3rd)
:ARG1 (s3t / thing
:ARG1-of (s3d2 / do-02
:ARG0 s3p
:ARG1-of
(s3w / wrong-02)
:aspect Process
:modpred s3d))
:modstr FullAff)
“He denied any wrongdoing”
125. The challenge: Integration of different meaning components
into one graph
► How do we represent all this information in a unified
structure that is still easy to read and scalable?
► UMR pairs a sentence-level representation (a modified
form of AMR) with a document-level representation.
► We assume that a text will still have to be processed
sentence by sentence, so each sentence will have a
fragment of the document-level super-structure.
126. Integrated UMR
representa6on
1. Edmund Pope tasted freedom today for the first time in
more than eight months.
2. Pope is the American businessman who was convicted last
week on spying charges and sentenced to 20 years in a
Russian prison.
3. He denied any wrongdoing.
127. Sentence-level representation vs document-level representation
(s1t2 / taste-01
:Aspect Performance
:ARG0 (s1p / person
:name (s1n2 / name
:op1 “Edmund”
:op2 “Pope”))
:ARG1 (s1f / free-04 :ARG1 s1p)
:time (s1t3 / today)
:ord (s1o3 / ordinal-entity
:value 1
:range (s1m / more-than
:op1 (s1t / temporal-quantity
:quant 8
:unit (s1m2 / month)))))
Edmund Pope tasted freedom today for the first time in
more than eight months.
(s1 / sentence
:temporal ((DCT :before
s1t2) (s1t3 :contained s1t2)
(DCT :depends-on s1t3))
:modal ((ROOT :MODALAUTH)
(AUTH :FullAff s1t2)))
128. Pope is the American businessman who was convicted last week on spying charges and sentenced to 20 years in a
Russian prison.
(s2i/ identity-91
:ARG0 (p/ person :wiki "Edmond_Pope"
:name (n/ name "op1 "Pope))
:ARG1 (b/ businessman
:mod (n2/ nationality :wiki "United_States"
:name (n3/ name :op1 "America")))
:ARG1-of (c/ convict-01
:ARG2 (c2/ charge-05
:ARG1b
:ARG2 (s/ spy-02
:ARG0b
:modpred c2))
:temporal (w/ week
:mod ( l / last))
:aspect Performance
:modstr FullAff)
:ARG1-of (s2/ sentence-01
:ARG2 (p2/ prison
:mod (c3/ country :wiki "Russia"
:name (n4/ name :op1 "Russia))
:duration ( t / temporal-quantity
:quant 20
:unit (y/ year)))
:ARG3s
:aspect Performance
:modstr FullAff)
:aspect State
:modstr FullAff)
( s2 / sentence
:temporal ((s2c4 :before s1t2)
(DCT :depends-on s2w)
(s2w :contained s2c
(s2w :contained s2s2)
(s2c :after s2s)
(s2s :after s2c4))
:modal ((AUTH :FullAff s2i)
(AUTH :FullAff s2c)
(AUTH :FullAff Null Charger)
(Null Charger :FullAff s2c2)
(s2c2 :Unsp s2s)
(AUTH :FullAff s2s2))
:coref ((s1p :same-entity s2p)))
Sentence-level representation vs document-level representation
131. From AMR to UMR Gysel et al. (2021)
► At the sentence level, UMR adds:
► An aspect attribute to eventive concepts
► Person and number attributes for pronouns and other nominal
expressions
► Quantification scope between quantified expressions
► At the document level UMR adds:
► Temporal dependencies in lieu of tense
► Modal dependencies in lieu of modality
► Coreference relations beyond sentence boundaries
► To make UMR cross-linguistically applicable, UMR
► defines a set of language-independent abstract concepts and
participant roles,
► uses lattices to accommodate linguistic variability
► designs specifications for complicated mappings between words and
UMR concepts.
132. Elements of AMR are already cross-linguistically
applicable
► Abstract concepts (e.g., person, thing, have-org-role-91):
► Abstract concepts are concepts that do not have explicit lexical support
but can be inferred from context
► Some semantic relations (e.g., :manner, :purpose, :time) are also
cross-linguistically applicable
133. Language-independent vs language-specific aspects of AMR
加入-01
person
董事会 date-entity
name
temporal-quantity
” 文肯”
” 皮埃尔”
61
岁
have-org-role-91
董事
11 29
Arg0
Arg1 time
name
op1
op2
age
quant
unit
Arg1-of
Arg0
Arg2
month day
mod
执行
polarity
-
“61 岁的 Pierre Vinken 将于 11 月 29 日加入董事会,担任
非执行董事。”
134. Language-independent vs language-specific aspects of AMR
join-01
person
board date-entity
name
temporal-quantity
”Vinken”
”Pierre”
61
year
have-org-role-91
director
11 29
Arg0
Arg1 time
name
op1
op2
age
quant
unit
Arg1-of
Arg0
Arg2
month day
mod
executive
polarity
-
““Pierre Vinken , 61 years old , will join the board as
a nonexecutive director Nov. 29 .”
135. Abstract concepts in UMR
► Abstract concepts inherited from AMR:
► Standardization of quantities, dates etc.: have-name-91,
have-frequency-91, have-quant-91, temporal-quantity, date-entity...
► New concepts for abstract events: “non-verbal” predication.
► New concepts for abstract entities: entity types are annotated for
named entities and implicit arguments.
► Scope: scope concept to disambiguate scope ambiguity to facilitate
translation of UMR to logical expressions (see sentence-level
structure).
► Discourse relations: concepts to capture sentence-internal discourse
relations (see sentence-level structure).
137. How do we find abstract eventive concepts?
► Languages use different strategies to express these meanings:
► Predicativized possessum: Yukaghir
pulun-die jowje-n'-i old.man-DIM net-PROP
3SG.INTR
`The old man has a net, lit. The old man net-
has.'
► UMR trains annotators to recognize the semantics of these constructions and
select the appropriate abstract predicate and its participant roles
138. Language-independent vs language-specific participant roles
► Core participant roles are defined in a set of frame files (valency
lexicon, see Palmer et al. 2005). The semantic roles for each
sense of a predicate are defined:
► E.g. boil-01: apply heat to water
ARG0-PAG: applier of heat ARG1-PPT:
water
► Most languages do not have frame files
► But see e.g. Hindi (Bhat et al. 2014), Chinese (Xue 2006)
► UMR defines language-independent participant roles
► Based on ValPaL data on co-expression patterns of different
micro-roles (Hartmann et al., 2013)
139. Language-independent roles: an incomplete list
UMR Annotation
Actor
Definition
animate entity that initiates the action
Undergoer
theme
Recipient
force
Causer
causer
experiencer
stimulus
entity (animate or inanimate) that is affected
by the action
entity (animate or inanimate) that moves from
one entity to another entity, either spatially or
metaphorically
animate entity that gains possession (or at
least temporary control) of another entity
inanimate entity that initiates the action
animate entity that acts on another animate
entity to initiate the action
animate entity that acts on another animate
entity to initiate the action
animate entity that cognitively or sensorily
experiences a stimulus
entity (animate or inanimate) that is experi-
enced by an experiencer
140. Road Map for annotating UMRs for under-
resourced languages
► Participant Roles:
► Stage 0: General participant roles
► Stage 1: Language-specific frame files
► UMR-Writer allows for the creation of lexicon with argument
structure information during annotation
► Morphosemantic Tests:
► Stage 0: Identify one concept per word
► Stage 1: Apply more fine-grained tests to identify concepts
► Annotation Categories with Lattices:
► Stage 0: Use grammatically encoded categories (more general if
necessary)
► Stage 1: Use (overtly expressed) fine-grained categories
► Modal Dependencies:
► Stage 0: Use simplified modal annotation
► Stage 1: Fill in lexically based modal strength values
141. How UMR accommodates cross-linguistic variability
► Not all languages grammaticalize/overtly express the same
meaning contrasts:
► English: I (1SG) vs. you (2SG) vs. she/he (3SG)
► Sanapaná: as- (1SG) vs. an-/ap- (2/3SG)
► However, there are typological patterns in how semantic
domains get subdivided:
► A 1/3SG person category would be much more surprising than a
2/3SG one
► UMR uses lattices for abstract concepts, attribute values, and
relations to accommodate variability across languages.
► Languages with overt grammatical distinctions can choose to use
more fine-grained categories
142. Lattic
es
►Semantic categories are organized in “lattices” to
achieve cross-lingual compatibility while
accommodating variability.
►We have lattices for abstract concepts, relations,
as well as attributes
Non-3rd Non-1st
1st 2nd 3rd
Excl. Incl.
person
143. Wordhood vs concepthood across languages
► The mapping between words and concepts in languages is
not one-to-one: UMR designs specifications for
complicated mappings between words and concepts.
► Multiple words can map to one concept (e.g., multi-word
expressions)
► One word can map to multiple concepts (morphological
complexity)
144. Multiple words can map to a single (discontinuous) concept
(x0/帮忙-01
:aspect Performance
:arg0 (x1/地理学)
:affectee (x2/我)
:degree (x3/大))
地理学帮 了我很大的忙。
“Geography has helped me a lot”
(w / want-01
:Aspect State
:ARG0 (p / person)
:ref-person 3rd
:ref-number Singular
:ARG1 (g / give-up-07
:ARG0 h
:ARG1 (t / that)
:aspect Performance
:modpred w)
:ARG1-of (c / cause-01
:ARG0 (a / umr-unknown))
:aspect State)
“Why would he want to give that up?”
145. One word maps to multiple UMR concepts
► One word containing predicate and arguments
Sanapaná:
yavhan anmen m-e-l-yen-ek
honey alcohol NEG-2/3M-DSTR-drink-POT
"They did not drink alcohol from honey."
(e / elyama
:actor (p / person
:ref-person 3rd
:ref-number Plural)
:undergoer (a / anmen
:material (y/ yavhan))
:modstr FullNeg
:aspect Habitual)
► Argument Indexation: Identify both predicate concept and
argument concept, don’t morphologically decompose word
146. One word maps to multiple UMR concepts
► One word containing predicate and arguments
Arapaho:
he'ih'iixooxookbixoh'oekoohuutoono' he'ih'ii-xoo-xook-
bixoh'oekoohuutoo-no'
NARR.PST.IPFV-REDUP-through-make.hand.appear.quickly-PL
``They were sticking their hands right through them [the ghosts] to the other
side.''
(b/ bixoh'oekoohuutoo `stick hands through'
:actor (p/ person :ref-person 3rd :ref-number Plural)
:theme (h/ hands)
:undergoer (g/ [ghosts])
:aspect Endeavor
:modstr FullAff)
► Noun Incorporation (less grammaticalized): identify predicate and
argument concept
147. UMR-Writer
► The annotation interface we use for UMR annotation is
called UMR-Writer
► UMR-Writer includes interfaces for project management,
sentence-level and document-level annotation, as well as
lexicon (frame file) creation.
► UMR-Writer has both keyboard-based and click-based
interfaces to accommodate the annotation habits of
different anntotators.
► UMR-Writer is web-based and supports UMR annotation
for avariety of languages and formats. Sofar it supports
Arabic, Arapaho, Chinese, English,Kukama Navajo, and
Sanapana. It can easily extended to more languages.
153. UMR summary
► UMR is a rooted directed node-labeled and edge-labeled
document-level graph.
► UMR is a document-level meaning representation that
builds on sentence-level meaning representations
► UMR aims to achieve semantic stability across syntactic
variations and support logical inference
► UMR is across-lingual meaning representation that
separates language-general aspects of meaning from those
that are language-specific
► We are doing UMR English, Chinese, Arabic, Arapaho,
Kukama, Sanapana, Navajo, Quechua
154. Use cases of UMR
► T
emporal reasoning
► UMR can be used to extract temporal dependencies, which
can then be used to perform temporal reasoning
► Knowledge extraction
► UMR annotates aspect, and this can be used to extract
habitual events or state, which are typical knowledge forms
► Factuality determination
► UMR annotates modal dependencies, and this can be used
to verify the factuality of events or claims
► As intermediate representation for dialogue systems where
control is more needed.
► UMR annotates entities and coreferences, which helps
tracking dialogue states
155. Planned UMR activities
• The DMR international workshops
• UMR summer schools, tentatively in 2024 and 2025.
• UMR shared tasks once we have sufficient amount of UMR-annotated data as
well as evaluation metrics and baseline parsing models
156. References
Banarescu, L., Bonial, C., Cai, S., Georgescu, M., Griffitt, K., Hermjakob, U., Knight, K., Koehn, P
., Palmer, M., and Schneider, N.
(2013). Abstract meaning representation for sembanking. In Proceedings of the 7th linguistic annotation workshop and
interoperability with discourse, pages 178–186.
Hartmann, I., Haspelmath, M., and Taylor, B., editors (2013). TheValency Patterns Leipzig online database. Max Planck Institute
for Evolutionary Anthropology, Leipzig.
Van Gysel, J. E. L., Vigus, M., Chun, J., Lai, K., Moeller, S., Yao, J., O’Gorman, T. J., Cowell,
A., Croft, W. B., Huang, C. R., Hajic, J., Martin, J. H., Oepen, S., Palmer, M., Pustejovsky, J.,Vallejos, R.,and Xue, N.
(2021). Designing auniform meaning representation for natural language processing. Künstliche Intelligenz, pages 1–
18.
Vigus, M., Van Gysel, J. E., and Croft, W. (2019). A dependency structure annotation for modality. In Proceedings of the First
International Workshop on Designing Meaning
Representations, pages 182–198.
Yao, J., Qiu, H., Min, B., and Xue, N. (2020). Annotating temporal dependency graphs via crowdsourcing. In Proceedings of the
2020 Conference on Empirical Methods in Natural LanguageProcessing (EMNLP), pages 5368–5380.
Yao, J., Qiu, H., Zhao, J., Min, B., and Xue, N. (2021). Factuality assessment as modal dependency parsing. In Proceedingsof
the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on
Natural Language Processing (Volume 1: Long Papers), pages 1540–1550.
Zhang, Y
. and Xue, N. (2018). Structured interpretation of temporal relations. In
Proceedings of LREC2018.
157. Acknowledgements
We would like to acknowledge the support of National Science Foundation:
• NSF IIS (2018): “Building a Uniform Meaning Representation for Natural Language
Processing” awarded to Brandeis (Xue, Pustejovsky), Colorado (M. Palmer, Martin, and
Cowell) and UNM (Croft).
• NSF CCRI (2022): ``Building a Broad Infrastructure for Uniform Meaning
Representations'', awarded to Brandeis (Xue, Pustejovsky) and Colorado (A. Palmer, M.
Palmer, cowell, Martin), with Croft as consultant
All views expressed in this paper are those of the authors and do not
necessarily represent the view of the National Science Foundation.
159. Meaning Representations for Natural Languages Tutorial Part 3a
Modeling Meaning Representation: SRL
Jeffrey Flanigan, Tim O’Gorman, Ishan Jindal, Yunyao Li, Martha Palmer, Nianwen Xue
160. Who did what to whom, when, where and how?
(Gildea and Jurafsky, 2000; Màrquez et al., 2008)
160
Semantic Role Labeling (SRL)
161. broke
Derik the window with a hammer to
161
Predicate Identification
1 Identify all predicates in the sentence
broke
Semantic Role Labeling (SRL)
escape
escape
162. break.01
broke
Predicate Identification
1
2
Identify all predicates in the sentence
Sense Disambiguation Classify sense of each predicate
162
break.01, break
A0: breaker
A1: thing broken
A2: instrument
A3: pieces
A4: arg1 broken
away from what?
English Propbank
Breaking_apart
Pieces
Whole
Criterion
Manner
Means
Place…
FrameNet Frame
Break-45.1
Agent
Patient
Instrument
Result
VerbNet
Semantic Role Labeling (SRL)
Derik the window with a hammer to escape.
163. break.01
Predicate Identification
1
2
3
Identify all predicates in the sentence
Sense Disambiguation Classify sense of each predicate
Argument Identification Find all roles of each predicate
163
Argument identification can either be
- Identification of span, (span SRL) OR
- Identification of head (dependency SRL)
broke
Semantic Role Labeling (SRL)
Derik the window with a hammer to escape
164. Predicate Identification
1
2
4
3
Identify all predicates in the sentence
Sense Disambiguation Classify sense of each predicate
Argument Identification Find all roles of each predicate
Argument Classification Assign semantic label to each role
164
Breaker thing broken
break.01 instrument Purpose
Semantic Role Labeling (SRL)
break.01
broke
Derik the window with a hammer to escape
165. Predicate Identification
1
2
4
3
Identify all predicates in the sentence
Sense Disambiguation Classify sense of each predicate
Argument Identification Find all roles of each predicate
Argument Classification Assign semantic label to each role
165
A0: Breaker A1: thing broken
break.01 A2: instrument AM-PRP: Purpose
Semantic Role Labeling (SRL)
break.01
broke
Derik the window with a hammer to escape
If using
PropBank
166. Predicate Identification
1
2
4
3
Identify all predicates in the sentence
Sense Disambiguation Classify sense of each predicate
Argument Identification Find all roles of each predicate
Argument Classification Assign semantic label to each role
166
A0: Breaker A1: thing broken
break.01 A2: instrument AM-PRP: Purpose
Semantic Role Labeling (SRL)
break.01
broke
Derik the window with a hammer to escape
5 Global Optimization Global constraints (predicates and arguments)
167. 167
Outline
q Early SRL approaches [< 2017]
q Typical neural SRL model components
q Performance analysis
q Syntax-aware neural SRL models
q What, When and Where?
q Performance analysis
q How to incorporate Syntax?
q Syntax-agnostic neural SRL models
q Performance Analysis
q Do we really need syntax for SRL?
q Are high quality contextual embedding enough for SRL
task?
q Practical SRL systems
q Should we rely on this pipelined approach?
q End-to-end SRL systems
q Can we jointly predict dependency and span?
q More recent approaches
q Handling low-frequency exceptions
q Incorporate semantic role label definitions
q SRL as MRC task
q Practical SRL system evaluations
q Are we evaluating SRL systems correctly?
q Conclusion
168. 168
Outline
q Early SRL approaches
q Typical neural SRL model components
q Performance analysis
q Syntax-aware neural SRL models
q What, When and Where?
q Performance analysis
q How to incorporate Syntax?
q Syntax-agnostic neural SRL models
q Performance Analysis
q Do we really need syntax for SRL?
q Are high quality contextual embedding enough for SRL
task?
q Practical SRL systems
q Should we rely on this pipelined approach?
q End-to-end SRL systems
q Can we jointly predict dependency and span?
q More recent approaches
q Handling low-frequency exceptions
q Incorporate semantic role label definitions
q SRL as MRC task
q Practical SRL system evaluations
q Are we evaluating SRL systems correctly?
q Conclusion
169. 169
Early SRL Approaches
Ø 2 to 3 steps to obtain complete predicate-
argument structure
Ø Predicate Identification
Ø Generally considered as not a task, as all the
existing SRL datasets provided Gold predicate
location.
Ø Predicate sense disambiguation
Ø Logistic Regression [Roth and Lapata, 2016]
Ø Argument Identification
Ø Binary classifier [Pradhan et al., 2005; Toutanova et
al., 2008]
Ø Role Labeling
Ø Labeling is performed using a classifier (SVM,
logistic regression)
Ø Argmax over roles will result in a local assignment
Ø Requires Feature Engineering
Ø Mostly Syntactic [Gildea and Jurafsky, 2002]
Ø Re-ranking
Ø Enforce linguiscc and structural constraint (e.g., no
overlaps, disconcnuous arguments, reference
arguments, ...)
Ø Viterbi decoding (k-best list with constraints)
[Täckström et al., 2015]
Ø Dynamic programming [Täckström et al., 2015;
Toutanova et al., 2008]
Ø Integer linear programming [Punyakanok et al.,
2008]
Ø Re-ranking [Toutanova et al., 2008; Bjö̈rkelund et
al., 2009]
170. 170
Outline
q Early SRL approaches
q Typical neural SRL model components
q Performance analysis
q Syntax-aware neural SRL models
q What, When and Where?
q Performance analysis
q How to incorporate Syntax?
q Syntax-agnostic neural SRL models
q Performance Analysis
q Do we really need syntax for SRL?
q Are high quality contextual embedding enough for SRL
task?
q Practical SRL systems
q Should we rely on this pipelined approach?
q End-to-end SRL systems
q Can we jointly predict dependency and span?
q More recent approaches
q Handling low-frequency exceptions
q Incorporate semantic role label definitions
q SRL as MRC task
q Practical SRL system evaluations
q Are we evaluating SRL systems correctly?
q Conclusion
171. Encoder
Classifier
Embedder
Input Sentence
Word embeddings
- FastText, GloVe
- ELMo, BERT
Types of encoder
- LSTMs, Attention
- MLP
Typical Neural SRL Components
171
A typical neural SRL model contains three
components
Ø Classifier
Ø Assign a semantic role label to each
token in the input sentence. [Local +
Global]
Ø Encoder:
Ø Encodes the context information to each
token.
Ø Embedder:
Ø Represent input token into continuous
vector representation.
172. Encoder
Classifier
Embedder
Input Sentence
Word embeddings
- FastText, GloVe
- ELMo, BERT
Neural SRL Components – Embedder
172
Ø Embedder:
Ø Represent input token into continuous
vector representation.
He had dared to defy nature
Embedder
Ø Could be static or dynamic embeddings
Ø Could include syntax information
Ø Usually, a binary flag
Ø 0 à represents no predicate
Ø 1 à represent predicate
End-to-end systems do not include this flag
173. Encoder
Classifier
Embedder
Input Sentence
Word embeddings
- FastText, GloVe
- ELMo, BERT Dynamic Embeddings
Merchant et al., 2020
Neural SRL Components – Embedder
Static Embeddings
GLoVe:
• He et al., 2017
• Strubell et al., 2018
SENNA:
• Ouchi et al., 2018
ELMo:
• Marcheggiani et al., 2017
• Ouchi et al., 2018
• Li et al., 2019
• Lyu et al., 2019
• Jindal et al., 2020
• Li et al., 2020
BERT:
• Shi et al., 2019
• Jindal et al., 2020
• Li et al., 2020
BERT:
• Shi et al., 2019
• Conia et al., 2020
• Zhang et al., 2021
• Tian et al., 2022
RoBERTa:
• Conia et al., 2020
• Blloshmi et al., 2021
• Fei et al., 2021
• Wang et al., 2022
• Zhang et al. 2022
XLNet:
• Zhou et al., 2020
• Tian et al., 2022
173
Ø Embedder:
Ø Represent input token into continuous
vector representation.
174. 85.28
89.6
91.4 91.5
92.6
93.3
70
75
80
85
90
95
100
Random GLoVe; Cai
et al., 2018
ELMo; Liet
al., 2019
BERT;
Conia et
al., 2020
BERT;
Conia et
al., 2020
RoBERTa;
Wang et
al., 2022
WSJ
F1
75.09
79.3
83.28
84.67
85.9
87.2
70
75
80
85
90
95
100
Random GLoVe; He
et al., 2018
ELMo; Liet
al., 2019
BERT;
Conia et
al., 2020
BERT;
Conia et
al., 2020
RoBERTa;
Wang et
al., 2022
Brown
F1
Static Static
Dataset: CoNLL09 EN
Performance Analysis
Best performing model for each word embedding type
174
175. Encoder
Classifier
Embedder
Input Sentence
Neural SRL Components – Encoder
175
Ø Encoder:
Ø Encodes the context information to each
token.
Types of encoder
- BiLSTMs
- Attention
He had dared to defy nature
Embedder
Encoder
Left pass
Right pass
Encoder could be
Ø Stacked BiLSTMs or some variant of LSTMs
Ø Attention Network
Ø Include syntax information
176. Encoder
Classifier
Embedder
Input Sentence
Neural SRL Components – Classifier
176
Ø Classifier
Ø Assign a semantic role label to each token
in the input sentence.
He had dared to defy nature
Embedder
Encoder
Usually a FF followed by Softmax
- MLP
Classifier
B-A0 0 0 B-A2 I-A2 I-A2
177. 177
Outline
q Early SRL approaches
q Typical neural SRL model components
q Performance analysis
q Syntax-aware neural SRL models
q What, When and Where?
q Performance analysis
q How to incorporate Syntax?
q Syntax-agnostic neural SRL models
q Performance Analysis
q Do we really need syntax for SRL?
q Are high quality contextual embedding enough for SRL
task?
q Prac/cal SRL systems
q Should we rely on this pipelined approach?
q End-to-end SRL systems
q Can we jointly predict dependency and span?
q More recent approaches
q Handling low-frequency excepcons
q Incorporate semancc role label definicons
q SRL as MRC task
q Prac/cal SRL system evalua/ons
q Are we evaluacng SRL systems correctly?
q Conclusion
178. 178
What and Where Syntax?
<latexit sha1_base64="DDfPssnDMCfvIPspxYHzFdvDzxQ=">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</latexit>
[Derick] broke the [window] with a [hammer] to [escape] .
Derick break the window with a hammer to escape .
PROPN VERB DET NOUN ADP DET NOUN PART VERB PUNT
nsubj det
obj mark
det
obl
mark
obl
ROOT
Surface form
Lemma form
U{X}POS
Dependency
Relation
Everything or anything that explains the syntactic structure of the sentence
Parsed with UDPipe Parser: hjp://lindat.mff.cuni.cz/services/udpipe/
What Syntax for SRL?
179. Syntax at Embedder
Concatenate {POS, dependency relation,
dependency head and other syntactic information}
Where the Syntax is being used?
Marcheggiani et al.,2017b
Li et al., 2018
He et al., 2018
Wang et al., 2019
Kasai et al., 2019
HE et al., 2019
Li et al., 2020
Zhou et al., 2020
179
Encoder
Classifier
Embedder
Input Sentence
Word embeddings
- FastText, GloVe
- ELMo, BERT
EMB
180. Syntax at Encoder
Dependency tree
- Graphs
- LSTMs Trees
Marcheggiani et al., 2017
Zhou et al., 2020
Marcheggiani et al., 2020
Zhang et al., 2021
Tian et al., 2022
180
Encoder
Classifier
Embedder
Input Sentence
Types of encoder
- BiLSTMs
- Attention
ENC
Where the Syntax is being used?
181. Joint Learning
At what level Syntax is used?
Strubell et al., 2018
Shi et al., 2020
Multi-task learning
181
Encoder
Classifier
Embedder
Input Sentence
Word embeddings
- FastText, GloVe
- ELMo, BERT
Types of encoder
- BiLSTMs
- Attention
- MLP
182. 87.7 88
89.5 89.8
90.2
90.86 90.99 91.27
91.7
92.83
80
82
84
86
88
90
92
94
Marcheggiani
et al.,2017b
Marcheggiani
et al., 2017
Heet al., 2018 LI et al., 2018 Kasaiet al.,
2019
HEet al., 2019 Lyu et al., 2019 Zhou et al.,
2020
LI et al., 2020 Fei et al., 2021
WSJ
F1
Dataset: CoNLL09 EN
2018 2019 2020 2021à
2017
Emb Enc Emb Emb Emb Emb
Enc
+
Emb
Enc
Emb
BERT/Fine-tune Regime
+2.0
-2.9
Comparing Syntax aware models
Performance Analysis
Enc
182
183. Dataset: CoNLL09 EN Comparing Syntax aware models
Observations
q Syntax at encoder level provides the best performance.
q Most likely, Encoder is best suited for incorporaOng dependency or consOtuent relaOons.
q BERT models raised the bar
q With Max improvement over Out-of-domain dataset
q However, the improvement since 2019 is marginal
183
184. A Simple and Accurate Syntax-Agnostic Neural Model for
Dependency-based Semantic Role Labeling
Marcheggiani et al., 2017
Ø Predict semantic dependency edges between
predicates and arguments.
Ø Use predicate-specific roles (such as make-A0
instead of A0) as opposed to generic sequence
labeling task.
184
Syntax at embedder level
Diego Marcheggiani, Anton Frolov, and Ivan Titov. 2017. A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling. In Proceedings of the 21st
Conference on Computational Natural Language Learning (CoNLL 2017), pages 411–420, Vancouver, Canada. Association for Computational Linguistics.
185. Marcheggiani et al., 2017
Wp
à
Randomly initialized word embeddings
Wr
à
Pre-trained word embeddings
PO
à
Randomly initialized POS embeddings
Le
à
Randomly initialized Lemma embeddings
à
Predicate specific feature [Binary]
Embedder OR
Input word representation
He had dared to defy nature
Embedder
185
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Syntax at embedder level
186. Marcheggiani et al., 2017
Encoder
He had dared to defy nature
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Embedder
Encoder
Several BiLSTMs layers
- Capturing both the left and the right context
- Each BiLSTM layer takes the lower layer as input
186
Syntax at embedder level
187. Marcheggiani et al., 2017
Preparation for classifier
Provide predicate hidden state as another another
input to classifier along with each token.
He had dared to defy nature
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Embedder
Encoder
+ ~6% F1 on CoNLL09 EN
187
The two ways of encoding predicate information,
using predicate-specific flag at embedder level and
incorporating the predicate state in the classifier,
turn out to be complementary.
Syntax at embedder level
Predicate
Hidden state
188. Marcheggiani et al., 2017
86.9
87.3 87.3
87.7 87.7
80
81
82
83
84
85
86
87
88
89
90
Bjö̈rkelund et al.
(2010)
Täckström et al.
(2015)
FitzGerald et al.
(2015)
Roth and Lapata
(2016)
Marcheggianiet
al. (2017)
WSJ
75.6 75.7 75.2
76.1
77.7
65
70
75
80
85
90
Bjö̈rkelund et
al. (2010)
Täckström et
al. (2015)
FitzGerald et
al. (2015)
Roth and
Lapata (2016)
Marcheggiani
et al. (2017)
Brown
188
Syntax at embedder level
Dataset: CoNLL09 EN
189. Marcheggiani et al., 2017
Takeaways
Ø Appending POS does help à approx. 1 F1 points gain
Ø Predicate specific encoding does help à approx. 6 F1 point
gain
Ø Quite effective for the classification of arguments which are
far from the predicate in terms of word distance.
Ø Noted: Substantial improvement on EN OOD over previous
works.
He had dared to defy nature
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Embedder
Encoder
Classifier
A0 0 0 0 A2 0
189
Syntax at embedder level
190. Encoding Sentences with Graph ConvoluOonal Networks for
SemanOc Role Labeling
Marcheggiani et al., 2017b
He had dared to defy nature
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Wp
Wr
PO
Le
Embedder
Encoder
Classifier
A0 0 0 0 A2 0
K layers GCN
Ø Basic SRL components remains the same as compared
to [Marcheggiani et al., 2017]
Ø GCN layers are inserted between Encoder and
Classifier.
Ø Re-encoding the encoder representations based
on syntactic structure of the sentence.
Ø Modeling syntactic dependency structure
190
Syntax at encoder level
Diego Marcheggiani and Ivan Titov. 2017. Encoding Sentences with Graph ConvoluAonal Networks for SemanAc Role Labeling. In Proceedings of the 2017 Conference on Empirical Methods in
Natural Language Processing, pages 1506–1515, Copenhagen, Denmark. AssociaAon for ComputaAonal LinguisAcs.
191. What is syntactic GCN?
Marcheggiani et al., 2017b
He had dared to defy nature
Ø Self Loops
Ø Allowing input feature representation of a node
affects its induced representation.
ReLU ReLU ReLU ReLU ReLU ReLU
nsubj
xcomp obj
aux mark
<latexit
sha1_base64="C7F53Y/OaV04lPikHNPSRzKAF7c=">AAACB3icbVC7SgNBFJ2Nrxhfq5aCDCZCbMJuELUM2lhGMA/IrmF2MpsMmX0wc1cMy3Y2/oqNhSK2/oKdf+PkUWjigYHDOfcx93ix4Aos69vILS2vrK7l1wsbm1vbO+buXlNFiaSsQSMRybZHFBM8ZA3gIFg7lowEnmAtb3g19lv3TCoehbcwipkbkH7IfU4JaKlrHpYc4AFTuHWXlu2TrJs6wB4g1RP9LCt1zaJVsSbAi8SekSKaod41v5xeRJOAhUAFUapjWzG4KZHAqWBZwUkUiwkdkj7raBoSvdtNJ3dk+FgrPexHUr8Q8ET93ZGSQKlR4OnKgMBAzXtj8T+vk4B/4aY8jBNgIZ0u8hOBIcLjUHCPS0ZBjDQhVHL9V0wHRBIKOrqCDsGeP3mRNKsV+6xyelMt1i5nceTRATpCZWSjc1RD16iOGoiiR/SMXtGb8WS8GO/Gx7Q0Z8x69tEfGJ8/bGeZDQ==</latexit>
⇥W
(1)
self
<latexit
sha1_base64="C7F53Y/OaV04lPikHNPSRzKAF7c=">AAACB3icbVC7SgNBFJ2Nrxhfq5aCDCZCbMJuELUM2lhGMA/IrmF2MpsMmX0wc1cMy3Y2/oqNhSK2/oKdf+PkUWjigYHDOfcx93ix4Aos69vILS2vrK7l1wsbm1vbO+buXlNFiaSsQSMRybZHFBM8ZA3gIFg7lowEnmAtb3g19lv3TCoehbcwipkbkH7IfU4JaKlrHpYc4AFTuHWXlu2TrJs6wB4g1RP9LCt1zaJVsSbAi8SekSKaod41v5xeRJOAhUAFUapjWzG4KZHAqWBZwUkUiwkdkj7raBoSvdtNJ3dk+FgrPexHUr8Q8ET93ZGSQKlR4OnKgMBAzXtj8T+vk4B/4aY8jBNgIZ0u8hOBIcLjUHCPS0ZBjDQhVHL9V0wHRBIKOrqCDsGeP3mRNKsV+6xyelMt1i5nceTRATpCZWSjc1RD16iOGoiiR/SMXtGb8WS8GO/Gx7Q0Z8x69tEfGJ8/bGeZDQ==</latexit>
⇥W
(1)
self
<latexit
sha1_base64="C7F53Y/OaV04lPikHNPSRzKAF7c=">AAACB3icbVC7SgNBFJ2Nrxhfq5aCDCZCbMJuELUM2lhGMA/IrmF2MpsMmX0wc1cMy3Y2/oqNhSK2/oKdf+PkUWjigYHDOfcx93ix4Aos69vILS2vrK7l1wsbm1vbO+buXlNFiaSsQSMRybZHFBM8ZA3gIFg7lowEnmAtb3g19lv3TCoehbcwipkbkH7IfU4JaKlrHpYc4AFTuHWXlu2TrJs6wB4g1RP9LCt1zaJVsSbAi8SekSKaod41v5xeRJOAhUAFUapjWzG4KZHAqWBZwUkUiwkdkj7raBoSvdtNJ3dk+FgrPexHUr8Q8ET93ZGSQKlR4OnKgMBAzXtj8T+vk4B/4aY8jBNgIZ0u8hOBIcLjUHCPS0ZBjDQhVHL9V0wHRBIKOrqCDsGeP3mRNKsV+6xyelMt1i5nceTRATpCZWSjc1RD16iOGoiiR/SMXtGb8WS8GO/Gx7Q0Z8x69tEfGJ8/bGeZDQ==</latexit>
⇥W
(1)
self
<latexit
sha1_base64="C7F53Y/OaV04lPikHNPSRzKAF7c=">AAACB3icbVC7SgNBFJ2Nrxhfq5aCDCZCbMJuELUM2lhGMA/IrmF2MpsMmX0wc1cMy3Y2/oqNhSK2/oKdf+PkUWjigYHDOfcx93ix4Aos69vILS2vrK7l1wsbm1vbO+buXlNFiaSsQSMRybZHFBM8ZA3gIFg7lowEnmAtb3g19lv3TCoehbcwipkbkH7IfU4JaKlrHpYc4AFTuHWXlu2TrJs6wB4g1RP9LCt1zaJVsSbAi8SekSKaod41v5xeRJOAhUAFUapjWzG4KZHAqWBZwUkUiwkdkj7raBoSvdtNJ3dk+FgrPexHUr8Q8ET93ZGSQKlR4OnKgMBAzXtj8T+vk4B/4aY8jBNgIZ0u8hOBIcLjUHCPS0ZBjDQhVHL9V0wHRBIKOrqCDsGeP3mRNKsV+6xyelMt1i5nceTRATpCZWSjc1RD16iOGoiiR/SMXtGb8WS8GO/Gx7Q0Z8x69tEfGJ8/bGeZDQ==</latexit>
⇥W
(1)
self
<latexit
sha1_base64="C7F53Y/OaV04lPikHNPSRzKAF7c=">AAACB3icbVC7SgNBFJ2Nrxhfq5aCDCZCbMJuELUM2lhGMA/IrmF2MpsMmX0wc1cMy3Y2/oqNhSK2/oKdf+PkUWjigYHDOfcx93ix4Aos69vILS2vrK7l1wsbm1vbO+buXlNFiaSsQSMRybZHFBM8ZA3gIFg7lowEnmAtb3g19lv3TCoehbcwipkbkH7IfU4JaKlrHpYc4AFTuHWXlu2TrJs6wB4g1RP9LCt1zaJVsSbAi8SekSKaod41v5xeRJOAhUAFUapjWzG4KZHAqWBZwUkUiwkdkj7raBoSvdtNJ3dk+FgrPexHUr8Q8ET93ZGSQKlR4OnKgMBAzXtj8T+vk4B/4aY8jBNgIZ0u8hOBIcLjUHCPS0ZBjDQhVHL9V0wHRBIKOrqCDsGeP3mRNKsV+6xyelMt1i5nceTRATpCZWSjc1RD16iOGoiiR/SMXtGb8WS8GO/Gx7Q0Z8x69tEfGJ8/bGeZDQ==</latexit>
⇥W
(1)
self
<latexit
sha1_base64="C7F53Y/OaV04lPikHNPSRzKAF7c=">AAACB3icbVC7SgNBFJ2Nrxhfq5aCDCZCbMJuELUM2lhGMA/IrmF2MpsMmX0wc1cMy3Y2/oqNhSK2/oKdf+PkUWjigYHDOfcx93ix4Aos69vILS2vrK7l1wsbm1vbO+buXlNFiaSsQSMRybZHFBM8ZA3gIFg7lowEnmAtb3g19lv3TCoehbcwipkbkH7IfU4JaKlrHpYc4AFTuHWXlu2TrJs6wB4g1RP9LCt1zaJVsSbAi8SekSKaod41v5xeRJOAhUAFUapjWzG4KZHAqWBZwUkUiwkdkj7raBoSvdtNJ3dk+FgrPexHUr8Q8ET93ZGSQKlR4OnKgMBAzXtj8T+vk4B/4aY8jBNgIZ0u8hOBIcLjUHCPS0ZBjDQhVHL9V0wHRBIKOrqCDsGeP3mRNKsV+6xyelMt1i5nceTRATpCZWSjc1RD16iOGoiiR/SMXtGb8WS8GO/Gx7Q0Z8x69tEfGJ8/bGeZDQ==</latexit>
⇥W
(1)
self
191
He(k+1) = He_self(k) +
Syntax at encoder level
192. Marcheggiani et al., 2017b
He had dared to defy nature
Ø SyntacOc children set of a node
ReLU ReLU ReLU ReLU ReLU ReLU
nsubj
xcomp obj
aux mark
<latexit
sha1_base64="C7F53Y/OaV04lPikHNPSRzKAF7c=">AAACB3icbVC7SgNBFJ2Nrxhfq5aCDCZCbMJuELUM2lhGMA/IrmF2MpsMmX0wc1cMy3Y2/oqNhSK2/oKdf+PkUWjigYHDOfcx93ix4Aos69vILS2vrK7l1wsbm1vbO+buXlNFiaSsQSMRybZHFBM8ZA3gIFg7lowEnmAtb3g19lv3TCoehbcwipkbkH7IfU4JaKlrHpYc4AFTuHWXlu2TrJs6wB4g1RP9LCt1zaJVsSbAi8SekSKaod41v5xeRJOAhUAFUapjWzG4KZHAqWBZwUkUiwkdkj7raBoSvdtNJ3dk+FgrPexHUr8Q8ET93ZGSQKlR4OnKgMBAzXtj8T+vk4B/4aY8jBNgIZ0u8hOBIcLjUHCPS0ZBjDQhVHL9V0wHRBIKOrqCDsGeP3mRNKsV+6xyelMt1i5nceTRATpCZWSjc1RD16iOGoiiR/SMXtGb8WS8GO/Gx7Q0Z8x69tEfGJ8/bGeZDQ==</latexit>
⇥W
(1)
self
<latexit
sha1_base64="C7F53Y/OaV04lPikHNPSRzKAF7c=">AAACB3icbVC7SgNBFJ2Nrxhfq5aCDCZCbMJuELUM2lhGMA/IrmF2MpsMmX0wc1cMy3Y2/oqNhSK2/oKdf+PkUWjigYHDOfcx93ix4Aos69vILS2vrK7l1wsbm1vbO+buXlNFiaSsQSMRybZHFBM8ZA3gIFg7lowEnmAtb3g19lv3TCoehbcwipkbkH7IfU4JaKlrHpYc4AFTuHWXlu2TrJs6wB4g1RP9LCt1zaJVsSbAi8SekSKaod41v5xeRJOAhUAFUapjWzG4KZHAqWBZwUkUiwkdkj7raBoSvdtNJ3dk+FgrPexHUr8Q8ET93ZGSQKlR4OnKgMBAzXtj8T+vk4B/4aY8jBNgIZ0u8hOBIcLjUHCPS0ZBjDQhVHL9V0wHRBIKOrqCDsGeP3mRNKsV+6xyelMt1i5nceTRATpCZWSjc1RD16iOGoiiR/SMXtGb8WS8GO/Gx7Q0Z8x69tEfGJ8/bGeZDQ==</latexit>
⇥W
(1)
self
<latexit
sha1_base64="C7F53Y/OaV04lPikHNPSRzKAF7c=">AAACB3icbVC7SgNBFJ2Nrxhfq5aCDCZCbMJuELUM2lhGMA/IrmF2MpsMmX0wc1cMy3Y2/oqNhSK2/oKdf+PkUWjigYHDOfcx93ix4Aos69vILS2vrK7l1wsbm1vbO+buXlNFiaSsQSMRybZHFBM8ZA3gIFg7lowEnmAtb3g19lv3TCoehbcwipkbkH7IfU4JaKlrHpYc4AFTuHWXlu2TrJs6wB4g1RP9LCt1zaJVsSbAi8SekSKaod41v5xeRJOAhUAFUapjWzG4KZHAqWBZwUkUiwkdkj7raBoSvdtNJ3dk+FgrPexHUr8Q8ET93ZGSQKlR4OnKgMBAzXtj8T+vk4B/4aY8jBNgIZ0u8hOBIcLjUHCPS0ZBjDQhVHL9V0wHRBIKOrqCDsGeP3mRNKsV+6xyelMt1i5nceTRATpCZWSjc1RD16iOGoiiR/SMXtGb8WS8GO/Gx7Q0Z8x69tEfGJ8/bGeZDQ==</latexit>
⇥W
(1)
self
<latexit
sha1_base64="C7F53Y/OaV04lPikHNPSRzKAF7c=">AAACB3icbVC7SgNBFJ2Nrxhfq5aCDCZCbMJuELUM2lhGMA/IrmF2MpsMmX0wc1cMy3Y2/oqNhSK2/oKdf+PkUWjigYHDOfcx93ix4Aos69vILS2vrK7l1wsbm1vbO+buXlNFiaSsQSMRybZHFBM8ZA3gIFg7lowEnmAtb3g19lv3TCoehbcwipkbkH7IfU4JaKlrHpYc4AFTuHWXlu2TrJs6wB4g1RP9LCt1zaJVsSbAi8SekSKaod41v5xeRJOAhUAFUapjWzG4KZHAqWBZwUkUiwkdkj7raBoSvdtNJ3dk+FgrPexHUr8Q8ET93ZGSQKlR4OnKgMBAzXtj8T+vk4B/4aY8jBNgIZ0u8hOBIcLjUHCPS0ZBjDQhVHL9V0wHRBIKOrqCDsGeP3mRNKsV+6xyelMt1i5nceTRATpCZWSjc1RD16iOGoiiR/SMXtGb8WS8GO/Gx7Q0Z8x69tEfGJ8/bGeZDQ==</latexit>
⇥W
(1)
self
<latexit
sha1_base64="C7F53Y/OaV04lPikHNPSRzKAF7c=">AAACB3icbVC7SgNBFJ2Nrxhfq5aCDCZCbMJuELUM2lhGMA/IrmF2MpsMmX0wc1cMy3Y2/oqNhSK2/oKdf+PkUWjigYHDOfcx93ix4Aos69vILS2vrK7l1wsbm1vbO+buXlNFiaSsQSMRybZHFBM8ZA3gIFg7lowEnmAtb3g19lv3TCoehbcwipkbkH7IfU4JaKlrHpYc4AFTuHWXlu2TrJs6wB4g1RP9LCt1zaJVsSbAi8SekSKaod41v5xeRJOAhUAFUapjWzG4KZHAqWBZwUkUiwkdkj7raBoSvdtNJ3dk+FgrPexHUr8Q8ET93ZGSQKlR4OnKgMBAzXtj8T+vk4B/4aY8jBNgIZ0u8hOBIcLjUHCPS0ZBjDQhVHL9V0wHRBIKOrqCDsGeP3mRNKsV+6xyelMt1i5nceTRATpCZWSjc1RD16iOGoiiR/SMXtGb8WS8GO/Gx7Q0Z8x69tEfGJ8/bGeZDQ==</latexit>
⇥W
(1)
self
<latexit
sha1_base64="C7F53Y/OaV04lPikHNPSRzKAF7c=">AAACB3icbVC7SgNBFJ2Nrxhfq5aCDCZCbMJuELUM2lhGMA/IrmF2MpsMmX0wc1cMy3Y2/oqNhSK2/oKdf+PkUWjigYHDOfcx93ix4Aos69vILS2vrK7l1wsbm1vbO+buXlNFiaSsQSMRybZHFBM8ZA3gIFg7lowEnmAtb3g19lv3TCoehbcwipkbkH7IfU4JaKlrHpYc4AFTuHWXlu2TrJs6wB4g1RP9LCt1zaJVsSbAi8SekSKaod41v5xeRJOAhUAFUapjWzG4KZHAqWBZwUkUiwkdkj7raBoSvdtNJ3dk+FgrPexHUr8Q8ET93ZGSQKlR4OnKgMBAzXtj8T+vk4B/4aY8jBNgIZ0u8hOBIcLjUHCPS0ZBjDQhVHL9V0wHRBIKOrqCDsGeP3mRNKsV+6xyelMt1i5nceTRATpCZWSjc1RD16iOGoiiR/SMXtGb8WS8GO/Gx7Q0Z8x69tEfGJ8/bGeZDQ==</latexit>
⇥W
(1)
self
<latexit
sha1_base64="aOP8/D4V8b2zsT12Nkq5uPRT3iM=">AAACB3icbVDLSgNBEJz1GeNr1aMgg4kQL2E3iHoMevEYwTwgiWF2MpuMmZ1dZnrFsOzNi7/ixYMiXv0Fb/6Nk8dBEwsaiqpuuru8SHANjvNtLSwuLa+sZtay6xubW9v2zm5Nh7GirEpDEaqGRzQTXLIqcBCsESlGAk+wuje4HPn1e6Y0D+UNDCPWDkhPcp9TAkbq2Af5FvCAaVy/TQrucdpJWsAeINGxd5em+Y6dc4rOGHieuFOSQ1NUOvZXqxvSOGASqCBaN10ngnZCFHAqWJptxZpFhA5IjzUNlcTsbifjP1J8ZJQu9kNlSgIeq78nEhJoPQw80xkQ6OtZbyT+5zVj8M/bCZdRDEzSySI/FhhCPAoFd7liFMTQEEIVN7di2ieKUDDRZU0I7uzL86RWKrqnxZPrUq58MY0jg/bRISogF52hMrpCFVRFFD2iZ/SK3qwn68V6tz4mrQvWdGYP/YH1+QN7w5kX</latexit>
⇥
W (1)
subj
<latexit
sha1_base64="8Gz0Mk/cy5pzqtj9WbX6+sEWlzg=">AAACCHicbVC7SgNBFJ31GeNr1dLCwUSITdgNopZBG8sI5gHZGGYns8mQ2QczdyVh2dLGX7GxUMTWT7Dzb5wkW2jigQuHc+7l3nvcSHAFlvVtLC2vrK6t5zbym1vbO7vm3n5DhbGkrE5DEcqWSxQTPGB14CBYK5KM+K5gTXd4PfGbD0wqHgZ3MI5Yxyf9gHucEtBS1zwqOsB9pnDzPinZp2k3cYCNIBnR0I/StNg1C1bZmgIvEjsjBZSh1jW/nF5IY58FQAVRqm1bEXQSIoFTwdK8EysWETokfdbWNCB6eSeZPpLiE630sBdKXQHgqfp7IiG+UmPf1Z0+gYGa9ybif147Bu+yk/AgioEFdLbIiwWGEE9SwT0uGQUx1oRQyfWtmA6IJBR0dnkdgj3/8iJpVMr2efnstlKoXmVx5NAhOkYlZKMLVEU3qIbqiKJH9Ixe0ZvxZLwY78bHrHXJyGYO0B8Ynz9aypmU</latexit>
⇥
W
(1)
xcom
p
<latexit
sha1_base64="LufH28OLnsOd0sNygmTE4R71Sdw=">AAACBnicbVDLSgNBEJz1GeMr6lGEwUSIl7AbRD0GvXiMYB6QrMvsZJIMmZ1dZnolYdmTF3/FiwdFvPoN3vwbJ4+DJhY0FFXddHf5keAabPvbWlpeWV1bz2xkN7e2d3Zze/t1HcaKshoNRaiaPtFMcMlqwEGwZqQYCXzBGv7geuw3HpjSPJR3MIqYG5Ce5F1OCRjJyx0V2sADpnHjPik6p6mXtIENISHxME0LXi5vl+wJ8CJxZiSPZqh6ua92J6RxwCRQQbRuOXYEbkIUcCpYmm3HmkWEDkiPtQyVxKx2k8kbKT4xSgd3Q2VKAp6ovycSEmg9CnzTGRDo63lvLP7ntWLoXroJl1EMTNLpom4sMIR4nAnucMUoiJEhhCpubsW0TxShYJLLmhCc+ZcXSb1ccs5LZ7flfOVqFkcGHaJjVEQOukAVdIOqqIYoekTP6BW9WU/Wi/VufUxbl6zZzAH6A+vzB7DamKc=</latexit>
⇥
W
(
1
)
a
u
x
192
What is syntacOc GCN?
He(k+1) = He_self(k) + He_child_of(k) +
Syntax at encoder level