Invited Keynote by Professor Noah A Smith (University of Washington) for ACL 2017. 1 Aug 2017. Vancouver, Canada.
Also available at https://homes.cs.washington.edu/~nasmith/slides/acl-8-1-17.pdf
License: CC BY 4.0
Delivered by Chris Callison Burch (University of Pennsylvania), Regina Barzilay (Massachusetts Institute of Technology) and Min-Yen Kan (National University of Singapore). 31 Aug 2017. Vancouver, Canada
Gender diversity on management and supervisory boardsGRAPE
Using a unique database of over 20 million firms over two decades, we examine industry sector and national institution drivers of the prevalence of women directors on supervisory and management boards in both public and private firms across advanced and emerging European economies. We demonstrate that gender board diversity has generally increased, yet women remain rare in both boards: approximately 70% of European firms have no women directors on their supervisory boards, and 60% have no women directors on management boards. We leverage institutional and resource dependency theoretical frameworks to demonstrate that few systematic factors are associated with greater gender diversity for both supervisory and management boards among both private and public firms: the same factor may exhibit a positive correlation to a management board, and a negative correlation to a supervisory board, or vice versa. We interpret these findings as evidence that country-level gender equality and cultural institutions exhibit differentiated correlations with the presence of women in management and supervisory boards. We also find little evidence that sector-level competition and innovativeness are systematically associated with presence of women on either board in either group of firms
Delivered by Chris Callison Burch (University of Pennsylvania), Regina Barzilay (Massachusetts Institute of Technology) and Min-Yen Kan (National University of Singapore). 31 Aug 2017. Vancouver, Canada
Gender diversity on management and supervisory boardsGRAPE
Using a unique database of over 20 million firms over two decades, we examine industry sector and national institution drivers of the prevalence of women directors on supervisory and management boards in both public and private firms across advanced and emerging European economies. We demonstrate that gender board diversity has generally increased, yet women remain rare in both boards: approximately 70% of European firms have no women directors on their supervisory boards, and 60% have no women directors on management boards. We leverage institutional and resource dependency theoretical frameworks to demonstrate that few systematic factors are associated with greater gender diversity for both supervisory and management boards among both private and public firms: the same factor may exhibit a positive correlation to a management board, and a negative correlation to a supervisory board, or vice versa. We interpret these findings as evidence that country-level gender equality and cultural institutions exhibit differentiated correlations with the presence of women in management and supervisory boards. We also find little evidence that sector-level competition and innovativeness are systematically associated with presence of women on either board in either group of firms
Tim Estes - Generating dynamic social networks from large scale unstructured ...Digital Reasoning
Tim Estes, CEO of Digital Reasoning, delivered this presentation at the Strata Conference (Feb 2011). It discusses how large scale blog data can be mined to yield social networks of influencers, connections, discussion topics, etc.
Talking to your Data: Natural Language Interfaces for a schema-less world (Ke...Andre Freitas
The increase in the size, heterogeneity and complexity of contemporary Big Data environments brings major challenges for the consumption of structured and semi–structured data. Addressing these challenges requires a convergence of approaches from different communities including databases, natural language processing, and information retrieval. Research on Natural Language Interfaces (NLI) and Question Answering systems has played a prominent role in stimulating a multidisciplinary approach to the problem that has moved the field from a futuristic vision to a concrete industry-level technological trend.
In this talk we distill the key principles of state-of-the-art approaches for data consumption using NLI. Particular attention is paid to the maturity and effectiveness of each approach together with discussion on future trends and active research questions.
This workshop was presented in Riyadh, SA in 21-22 Jan 2019, with the collaboration with Riyadh Data Geeks group.
To learn more about the workshop please see this website:
http://bit.ly/2Ucjmm5
Building AI Applications using Knowledge GraphsAndre Freitas
Goals of this Tutorial:
Provide a broad view of the multiple perspectives underlying knowledge graphs.
Show knowledge graphs as a foundation for building AI systems.
Method:
Focus on the contemporary and emerging perspectives.
Sampling exemplar approaches and infrastructures on each of these emerging perspectives (not an exhaustive survey).
Slides for the course Big Data and Automated Content Analysis, in which students of the social sciences (communication science) learn how to conduct analyses using Python.
What data scientists really do, according to 50 data scientistsHugo Bowne-Anderson
My talk at PyData NYC, 2018.
This is the abstract:
Hugo Bowne-Anderson, data scientist and host of the DataFramed podcast, will give you a view into the thinking of 50 leading data scientists from around the world about the trends driving the data science revolution. During his interviews with these thought leaders, Hugo discovered themes and lessons about the past, present, and future of data science.
Why Watson Won: A cognitive perspectiveJames Hendler
In this talk, we present how the Watson program, IBM's famous Jeopardy playing computer, works (based on papers published by IBM), we look at some aspects of potential scoring approaches, and we examine how Watson compares to several well known systems and some preliminary thoughts on using it in future artificial intelligence and cognitive science approaches.
How do we protect privacy of users in large-scale systems? How do we ensure fairness and transparency when developing machine learned models? With the ongoing explosive growth of AI/ML models and systems, these are some of the ethical and legal challenges encountered by researchers and practitioners alike. In this talk (presented at QConSF 2018), we first present an overview of privacy breaches as well as algorithmic bias / discrimination issues observed in the Internet industry over the last few years and the lessons learned, key regulations and laws, and evolution of techniques for achieving privacy and fairness in data-driven systems. We motivate the need for adopting a "privacy and fairness by design" approach when developing data-driven AI/ML models and systems for different consumer and enterprise applications. We also focus on the application of privacy-preserving data mining and fairness-aware machine learning techniques in practice, by presenting case studies spanning different LinkedIn applications, and conclude with the key takeaways and open challenges.
This workshop was presented in Riyadh, SA in 21-22 Jan 2019, with the collaboration with Riyadh Data Geeks group.
To learn more about the workshop please see this website:
http://bit.ly/2Ucjmm5
Using modern machine learning methods, Christian shows how a million comments can be structured and information can be extracted.
He will use Python and Jupyter notebooks and visualizations as results.
Trainer: Christian Winkler holds a PhD in Theoretical Physics. He has worked in software and AI for 20 years, specializing in intelligent algorithms for unstructured data and text. He is a frequent speaker at conference and author of many articles and tutorials.
Tim Estes - Generating dynamic social networks from large scale unstructured ...Digital Reasoning
Tim Estes, CEO of Digital Reasoning, delivered this presentation at the Strata Conference (Feb 2011). It discusses how large scale blog data can be mined to yield social networks of influencers, connections, discussion topics, etc.
Talking to your Data: Natural Language Interfaces for a schema-less world (Ke...Andre Freitas
The increase in the size, heterogeneity and complexity of contemporary Big Data environments brings major challenges for the consumption of structured and semi–structured data. Addressing these challenges requires a convergence of approaches from different communities including databases, natural language processing, and information retrieval. Research on Natural Language Interfaces (NLI) and Question Answering systems has played a prominent role in stimulating a multidisciplinary approach to the problem that has moved the field from a futuristic vision to a concrete industry-level technological trend.
In this talk we distill the key principles of state-of-the-art approaches for data consumption using NLI. Particular attention is paid to the maturity and effectiveness of each approach together with discussion on future trends and active research questions.
This workshop was presented in Riyadh, SA in 21-22 Jan 2019, with the collaboration with Riyadh Data Geeks group.
To learn more about the workshop please see this website:
http://bit.ly/2Ucjmm5
Building AI Applications using Knowledge GraphsAndre Freitas
Goals of this Tutorial:
Provide a broad view of the multiple perspectives underlying knowledge graphs.
Show knowledge graphs as a foundation for building AI systems.
Method:
Focus on the contemporary and emerging perspectives.
Sampling exemplar approaches and infrastructures on each of these emerging perspectives (not an exhaustive survey).
Slides for the course Big Data and Automated Content Analysis, in which students of the social sciences (communication science) learn how to conduct analyses using Python.
What data scientists really do, according to 50 data scientistsHugo Bowne-Anderson
My talk at PyData NYC, 2018.
This is the abstract:
Hugo Bowne-Anderson, data scientist and host of the DataFramed podcast, will give you a view into the thinking of 50 leading data scientists from around the world about the trends driving the data science revolution. During his interviews with these thought leaders, Hugo discovered themes and lessons about the past, present, and future of data science.
Why Watson Won: A cognitive perspectiveJames Hendler
In this talk, we present how the Watson program, IBM's famous Jeopardy playing computer, works (based on papers published by IBM), we look at some aspects of potential scoring approaches, and we examine how Watson compares to several well known systems and some preliminary thoughts on using it in future artificial intelligence and cognitive science approaches.
How do we protect privacy of users in large-scale systems? How do we ensure fairness and transparency when developing machine learned models? With the ongoing explosive growth of AI/ML models and systems, these are some of the ethical and legal challenges encountered by researchers and practitioners alike. In this talk (presented at QConSF 2018), we first present an overview of privacy breaches as well as algorithmic bias / discrimination issues observed in the Internet industry over the last few years and the lessons learned, key regulations and laws, and evolution of techniques for achieving privacy and fairness in data-driven systems. We motivate the need for adopting a "privacy and fairness by design" approach when developing data-driven AI/ML models and systems for different consumer and enterprise applications. We also focus on the application of privacy-preserving data mining and fairness-aware machine learning techniques in practice, by presenting case studies spanning different LinkedIn applications, and conclude with the key takeaways and open challenges.
This workshop was presented in Riyadh, SA in 21-22 Jan 2019, with the collaboration with Riyadh Data Geeks group.
To learn more about the workshop please see this website:
http://bit.ly/2Ucjmm5
Using modern machine learning methods, Christian shows how a million comments can be structured and information can be extracted.
He will use Python and Jupyter notebooks and visualizations as results.
Trainer: Christian Winkler holds a PhD in Theoretical Physics. He has worked in software and AI for 20 years, specializing in intelligent algorithms for unstructured data and text. He is a frequent speaker at conference and author of many articles and tutorials.
Operation “Blue Star” is the only event in the history of Independent India where the state went into war with its own people. Even after about 40 years it is not clear if it was culmination of states anger over people of the region, a political game of power or start of dictatorial chapter in the democratic setup.
The people of Punjab felt alienated from main stream due to denial of their just demands during a long democratic struggle since independence. As it happen all over the word, it led to militant struggle with great loss of lives of military, police and civilian personnel. Killing of Indira Gandhi and massacre of innocent Sikhs in Delhi and other India cities was also associated with this movement.
Biological screening of herbal drugs: Introduction and Need for
Phyto-Pharmacological Screening, New Strategies for evaluating
Natural Products, In vitro evaluation techniques for Antioxidants, Antimicrobial and Anticancer drugs. In vivo evaluation techniques
for Anti-inflammatory, Antiulcer, Anticancer, Wound healing, Antidiabetic, Hepatoprotective, Cardio protective, Diuretics and
Antifertility, Toxicity studies as per OECD guidelines
How to Make a Field invisible in Odoo 17Celine George
It is possible to hide or invisible some fields in odoo. Commonly using “invisible” attribute in the field definition to invisible the fields. This slide will show how to make a field invisible in odoo 17.
Embracing GenAI - A Strategic ImperativePeter Windle
Artificial Intelligence (AI) technologies such as Generative AI, Image Generators and Large Language Models have had a dramatic impact on teaching, learning and assessment over the past 18 months. The most immediate threat AI posed was to Academic Integrity with Higher Education Institutes (HEIs) focusing their efforts on combating the use of GenAI in assessment. Guidelines were developed for staff and students, policies put in place too. Innovative educators have forged paths in the use of Generative AI for teaching, learning and assessments leading to pockets of transformation springing up across HEIs, often with little or no top-down guidance, support or direction.
This Gasta posits a strategic approach to integrating AI into HEIs to prepare staff, students and the curriculum for an evolving world and workplace. We will highlight the advantages of working with these technologies beyond the realm of teaching, learning and assessment by considering prompt engineering skills, industry impact, curriculum changes, and the need for staff upskilling. In contrast, not engaging strategically with Generative AI poses risks, including falling behind peers, missed opportunities and failing to ensure our graduates remain employable. The rapid evolution of AI technologies necessitates a proactive and strategic approach if we are to remain relevant.
The French Revolution, which began in 1789, was a period of radical social and political upheaval in France. It marked the decline of absolute monarchies, the rise of secular and democratic republics, and the eventual rise of Napoleon Bonaparte. This revolutionary period is crucial in understanding the transition from feudalism to modernity in Europe.
For more information, visit-www.vavaclasses.com
Acetabularia Information For Class 9 .docxvaibhavrinwa19
Acetabularia acetabulum is a single-celled green alga that in its vegetative state is morphologically differentiated into a basal rhizoid and an axially elongated stalk, which bears whorls of branching hairs. The single diploid nucleus resides in the rhizoid.
Exploiting Artificial Intelligence for Empowering Researchers and Faculty, In...Dr. Vinod Kumar Kanvaria
Exploiting Artificial Intelligence for Empowering Researchers and Faculty,
International FDP on Fundamentals of Research in Social Sciences
at Integral University, Lucknow, 06.06.2024
By Dr. Vinod Kumar Kanvaria
Macroeconomics- Movie Location
This will be used as part of your Personal Professional Portfolio once graded.
Objective:
Prepare a presentation or a paper using research, basic comparative analysis, data organization and application of economic information. You will make an informed assessment of an economic climate outside of the United States to accomplish an entertainment industry objective.
Azure Interview Questions and Answers PDF By ScholarHat
Noah A Smith - 2017 - Invited Keynote: Squashing Computational Linguistics
1. Squashing
Computational Linguistics
Noah A. Smith
Paul G. Allen School of Computer Science & Engineering
University of Washington
Seattle, USA
@nlpnoah
Research supported in part by: NSF, DARPA DEFT, DARPA CWC, Facebook, Google, Samsung, University of Washington.
3. Applications of NLP in 2017
• Conversation, IE, MT, QA, summarization, text categorization
4. Applications of NLP in 2017
• Conversation, IE, MT, QA, summarization, text categorization
• Machine-in-the-loop tools for (human) authors
Elizabeth Clark
Collaborate with an NLP
model through an
“exquisite corpse”
storytelling game
Chenhao Tan
Revise your
message with help
from NLP
tremoloop.com
5. Applications of NLP in 2017
• Conversation, IE, MT, QA, summarization, text categorization
• Machine-in-the-loop tools for (human) authors
• Analysis tools for measuring social phenomena
Lucy Lin
Sensationalism in
science news
bit.ly/sensational-news
… bookmark this survey!
Dallas Card
Track ideas, propositions,
frames in discourse over
time
8. Squash Networks
• Parameterized differentiable functions composed out of simpler
parameterized differentiable functions, some nonlinear
9. Squash Networks
• Parameterized differentiable functions composed out of simpler
parameterized differentiable functions, some nonlinear
From Jack (2010),Dynamic
System Modeling and
Control, goo.gl/pGvJPS
*Yes, rectified linear units (relus) are only half-squash; hat-tip Martha White.
10. Squash Networks
• Parameterized differentiable functions composed out of simpler
parameterized differentiable functions, some nonlinear
• Estimate parameters using Leibniz (1676)
From existentialcomics.com
11. Who wants an all-squash diet?
wow
very Curcurbita
much festive
many dropout
20. “gold” output
Linguistic Structure Prediction
input representation
input (text)
part representations
output (structure)
training objective
clusters,lexicons,
embeddings, …
sequences,
trees,
graphs, …
probabilistic,
cost-aware,…
21. “gold” output
Linguistic Structure Prediction
input representation
input (text)
part representations
output (structure)
training objective
clusters,lexicons,
embeddings, …
segments/spans, arcs,
graph fragments, …
sequences,
trees,
graphs, …
probabilistic,
cost-aware,…
22. “gold” output
Linguistic Structure Prediction
input representation
input (text)
part representations
output (structure)
training objective
23. “gold” output
Linguistic Structure Prediction
input representation
input (text)
part representations
output (structure)
training objective
error definitions
& weights
regularization
annotation
conventions
& theory
constraints &
independence
assumptions
dataselection
“task”
24. Inductive Bias
• What does your learning
algorithm assume?
• How will it choose among good
predictive functions?
See also:
No Free Lunch Theorem
(Mitchell, 1980;Wolpert, 1996)
26. Three New Models
• Parsing sentences into
predicate-argument structures
• Fillmore frames
• Semantic dependency graphs
• Language models that
dynamically track entities
27. When Democrats wonder why there is so much resentment of Clinton, they don’t need to look much
further than the Big Lie about philandering that Stephanopoulos, Carville helped to put over in 1992.
Original story on Slate.com: http://goo.gl/Hp89tD
28. Frame-Semantic Analysis
When Democrats wonder why there is so much resentment of Clinton, they don’t need to look much
further than the Big Lie about philandering that Stephanopoulos, Carville helped to put over in 1992.
FrameNet: https://framenet.icsi.berkeley.edu
29. Frame-Semantic Analysis
When Democrats wonder why there is so much resentment of Clinton, they don’t need to look much
further than the Big Lie about philandering that Stephanopoulos, Carville helped to put over in 1992.
FrameNet: https://framenet.icsi.berkeley.edu
30. Frame-Semantic Analysis
When Democrats wonder why there is so much resentment of Clinton, they don’t need to look much
further than the Big Lie about philandering that Stephanopoulos, Carville helped to put over in 1992.
cognizer: Democrats
topic: why … Clinton
FrameNet: https://framenet.icsi.berkeley.edu
31. Frame-Semantic Analysis
When Democrats wonder why there is so much resentment of Clinton, they don’t need to look much
further than the Big Lie about philandering that Stephanopoulos, Carville helped to put over in 1992.
cognizer: Democrats
topic: why … Clinton
explanation: why
degree: so much
content: of Clinton
experiencer: ?
helper: Stephanopoulos … Carville
goal: to put over
time: in 1992
benefited_party: ?
FrameNet: https://framenet.icsi.berkeley.edu
landmark event: Democrats … Clinton
trajector event: they… 1992
entity: so … Clinton
degree: so
mass: resentment of Clinton
time: When … Clinton
required situation: they … to look … 1992
time: When … Clinton
cognizer agent: they
ground: much … 1992
sought entity: ?
topic: about … 1992
trajector event: the Big Lie … over
landmark period: 1992
33. Frame-Semantic Analysis
When Democrats wonder why there is so much resentment of Clinton, they don’t need to look much
further than the Big Lie about philandering that Stephanopoulos, Carville helped to put over in 1992.
cognizer: Democrats
topic: why … Clinton
explanation: why
degree: so much
content: of Clinton
experiencer: ?
helper: Stephanopoulos … Carville
goal: to put over
time: in 1992
benefited_party: ?
FrameNet: https://framenet.icsi.berkeley.edu
landmark event: Democrats … Clinton
trajector event: they… 1992
entity: so … Clinton
degree: so
mass: resentment of Clinton
time: When … Clinton
required situation: they … to look … 1992
time: When … Clinton
cognizer agent: they
ground: much … 1992
sought entity: ?
topic: about … 1992
trajector event: the Big Lie … over
landmark period: 1992
35. When Democrats wonderCogitation why there is so much resentment of Clinton, they don’t need …
biLSTM
(contextualized
word vectors)
words + frame
36. parts: segments
up to length d
scored by
another biLSTM,
with labels
When Democrats wonderCogitation why there is so much resentment of Clinton, they don’t need …
…
biLSTM
(contextualized
word vectors)
words + frame
37. parts: segments
up to length d
scored by
another biLSTM,
with labels
When Democrats wonderCogitation why there is so much resentment of Clinton, they don’t need …
…
biLSTM
(contextualized
word vectors)
words + frame
output: covering sequence of nonoverlapping segments
38. Segmental RNN
(Lingpeng Kong, Chris Dyer, N.A.S., ICLR 2016)
biLSTM
(contextualized
word vectors)
input sequence
parts: segments
up to length d
scored by
another biLSTM,
with labels
training objective:
log loss
output: covering sequence of nonoverlapping segments, recovered in O(Ldn); see Sarawagi & Cohen, 2004
…
42. When Democrats wonderCogitation why there is so much resentment of Clinton, they don’t need …
cognizer topic ∅
wonderCogitation
∅
wonderCogitation
wonderCogitation
wonderCogitation
∅
43. When Democrats wonderCogitation why there is so much resentment of Clinton, they don’t need …
cognizer topic ∅
wonderCogitation
∅
wonderCogitation
wonderCogitation
wonderCogitation
∅
44. When Democrats wonderCogitation why there is so much resentment of Clinton, they don’t need …
cognizer topic ∅
wonderCogitation
∅
wonderCogitation
wonderCogitation
wonderCogitation
∅
45. When Democrats wonderCogitation why there is so much resentment of Clinton, they don’t need …
cognizer topic ∅
wonderCogitation
∅
wonderCogitation
wonderCogitation
wonderCogitation
∅
46. Inference via dynamic programming in O(Ldn)
When Democrats wonderCogitation why there is so much resentment of Clinton, they don’t need …
cognizer topic ∅
wonderCogitation
∅
wonderCogitation
wonderCogitation
wonderCogitation
∅
47. Open-SESAME
(Swabha Swayamdipta, Sam Thomson,
Chris Dyer, N.A.S., arXiv:1706.09528)
biLSTM
(contextualized
word vectors)
words + frame
parts: segments
with role labels,
scored by
another biLSTM
training objective:
recall-oriented
softmax margin
(Gimpel et al.,
2010)
output: labeled
argument spans
When Democrats wonderCogitation why there is so much resentment of Clinton, they don’t need …
cognizer: Democrats
topic: why there is so much resentment of Clinton
…
48. When Democrats wonderCogitation why there is so much resentment of Clinton, they don’t need …
cognizer topic ∅
wonderCogitation
∅
wonderCogitation
wonderCogitation
wonderCogitation
∅
49. When Democrats wonderCogitation why there is so much resentment of Clinton, they don’t need …
cognizer topic ∅
wonderCogitation
∅
wonderCogitation
wonderCogitation
wonderCogitation
∅
syntax features?
50. When Democrats wonderCogitation why there is so much resentment of Clinton, they don’t need …
yes no yes yesno
Penn Treebank (Marcus et al., 1993)
51. When Democrats wonderCogitation why there is so much resentment of Clinton, they don’t need …
cognizer topic ∅
wonderCogitation
∅
wonderCogitation
wonderCogitation
wonderCogitation
∅
main task
scaffold task
yes no yes yesno
52. Multitask Representation Learning
(Caruana, 1997)
“gold” output
input representation
input (text)
part representations
output (structure)
training objective
“gold” output
input representation
input (text)
part representations
output (structure)
training objective
main task: find and
label semantic
arguments
scaffold task: predict
syntactic constituents
shared
training datasets need not overlap
output structures need not be consistent
53. ours
65
66
67
68
69
70
71
72
SEMAFOR 1.0
(Das et al.,
2014)
SEMAFOR 2.0
(Kshirsagar et
al.,2015)
Open-SESAME … with
syntactic
scaffold
… with syntax
features
Framat (Roth,
2016)
FitzGerald et
al. (2015)
single model ensemble
F1 on frame-semantic parsing (frames & arguments), FrameNet 1.5 test set.
open-source systems
54. ours
65
66
67
68
69
70
71
72
SEMAFOR 1.0
(Das et al.,
2014)
SEMAFOR 2.0
(Kshirsagar et
al.,2015)
Open-SESAME … with
syntactic
scaffold
… with syntax
features
Framat (Roth,
2016)
FitzGerald et
al. (2015)
single model ensemble
F1 on frame-semantic parsing (frames & arguments), FrameNet 1.5 test set.
open-source systems
55. biLSTM
(contextualized
word vectors)
words + frame
training objective:
recall-oriented
softmax margin
(Gimpel et al.,
2010)
output: labeled
argument spans
When Democrats wonderCogitation why there is so much resentment of Clinton, they don’t need …
cognizer: Democrats
topic: why there is so much resentment of Clinton
…
segments
get scores
Bias?
parts: segments
with role labels,
scored by
another biLSTM
56. biLSTM
(contextualized
word vectors)
words + frame
training objective:
recall-oriented
softmax margin
(Gimpel et al.,
2010)
output: labeled
argument spans
When Democrats wonderCogitation why there is so much resentment of Clinton, they don’t need …
cognizer: Democrats
topic: why there is so much resentment of Clinton
…
segments
get scores
syntactic scaffold
Bias?
parts: segments
with role labels,
scored by
another biLSTM
57. biLSTM
(contextualized
word vectors)
words + frame
training objective:
recall-oriented
softmax margin
(Gimpel et al.,
2010)
output: labeled
argument spans
When Democrats wonderCogitation why there is so much resentment of Clinton, they don’t need …
cognizer: Democrats
topic: why there is so much resentment of Clinton
…
segments
get scores
recall-oriented
cost
syntactic scaffold
Bias?
parts: segments
with role labels,
scored by
another biLSTM
58. Semantic Dependency Graphs
(DELPH-IN minimal recursion semantics-derived representation; “DM”)
Oepen et al. (SemEval 2014; 2015),see also http://sdp.delph-in.net
59. When Democrats wonderwhy there is so much resentment of Clinton, they don’t need …
Democrats wonder
arg1
tanh(C[hwonder; hDemocrats] + b) · arg1
60. When Democrats wonderwhy there is so much resentment of Clinton, they don’t need …
When Democrats Democrats wonder why is
is resentment
so much much resentment
resentment of of Clinton
arg2 arg1
arg1
comp_so
arg1
arg1 arg1arg1
61. When Democrats wonderwhy there is so much resentment of Clinton, they don’t need …
When Democrats
wonder why
Democrats wonder why is
is resentment
so much much resentment
resentment of of Clinton
arg2 arg1
arg1
comp_so
arg1
arg1
arg1 arg1arg1
wonder there
arg1
wonder is
arg1
62. When Democrats wonderwhy there is so much resentment of Clinton, they don’t need …
Inference via AD3
(alternating directions dual decomposition; Martins et al., 2014)
When Democrats
wonder why
Democrats wonder why is
is resentment
so much much resentment
resentment of of Clinton
arg2 arg1
arg1
comp_so
arg1
arg1
arg1 arg1arg1
wonder there
arg1
wonder is
arg1
63. Neurboparser
(Hao Peng, Sam Thomson, N.A.S., ACL 2017)
biLSTM
(contextualized
word vectors)
words
parts: labeled
bilexical
dependencies
training objective:
structured hinge
loss
output: labeled
semantic
dependency
graph with
constraints
When Democrats wonderwhy there is so much resentment of Clinton, they don’t need …
…
64. When Democrats wonderwhy there is so much resentment of Clinton, they don’t need …
Three Formalisms, Three Separate Parsers
Democrats wonder
arg1
formalism 3 (PSD)
formalism 2 (PAS)
formalism 1 (DM)
Democrats wonder
arg1
Democrats wonder
act
65. When Democrats wonderwhy there is so much resentment of Clinton, they don’t need …
Shared Input Representations
(Daumé, 2007)
Democrats wonder
arg1
shared across all
formalism 3 (PSD)
formalism 2 (PAS)
formalism 1 (DM)
Democrats wonder
arg1
Democrats wonder
act
66. When Democrats wonderwhy there is so much resentment of Clinton, they don’t need …
Cross-Task Parts
Democrats wonder
arg1
Democrats wonder
arg1
Democrats wonder
act
shared across all
67. When Democrats wonderwhy there is so much resentment of Clinton, they don’t need …
Both: Shared Input Representations
& Cross-Task Parts
Democrats wonder
arg1
shared across all
formalism 3 (PSD)
formalism 2 (PAS)
formalism 1 (DM)
Democrats wonder
arg1
Democrats wonder
act
69. ours
80
81
82
83
84
85
86
87
88
Du et al.,2015 Almeida &
Martins, 2015
(no syntax)
Almeida &
Martins, 2015
(syntax)
Neurboparser … with shared
input
representations
and cross-task
parts
WSJ (in-domain) Brown (out-of-domain)
F1 averaged on three semantic dependency parsing formalisms, SemEval 2015 test set.
70. 50
60
70
80
90
100
DM PAS PSD
WSJ (in-domain) Brown (out-of-domain)
Neurboparser F1 on three semantic dependency parsing formalisms, SemEval 2015 test set.
good enough?
71. biLSTM
(contextualized
word vectors)
words
training objective:
structured hinge
loss
output: labeled
semantic
dependency
graph with
constraints
When Democrats wonderwhy there is so much resentment of Clinton, they don’t need …
…
Bias? cross-formalism
sharing
parts: labeled
bilexical
dependencies
76. When Democrats wonderwhy there is so much resentment of
Entity Language Model
(Yangfeng Ji, Chenhao Tan, Sebastian Martschat,
Yejin Choi, N.A.S., EMNLP 2017)
77. Entity Language Model
(Yangfeng Ji, Chenhao Tan, Sebastian Martschat,
Yejin Choi, N.A.S., EMNLP 2017)
When Democrats wonderwhy there is so much resentment of
entity 1
78. Entity Language Model
(Yangfeng Ji, Chenhao Tan, Sebastian Martschat,
Yejin Choi, N.A.S., EMNLP 2017)
When Democrats wonderwhy there is so much resentment of Clinton,
1. new entity with new
vector
2. mention word will be
“Clinton”
entity 1
entity 2
79. Entity Language Model
(Yangfeng Ji, Chenhao Tan, Sebastian Martschat,
Yejin Choi, N.A.S., EMNLP 2017)
When Democrats wonderwhy there is so much resentment of Clinton,
entity 1
entity 2
80. Entity Language Model
(Yangfeng Ji, Chenhao Tan, Sebastian Martschat,
Yejin Choi, N.A.S., EMNLP 2017)
When Democrats wonderwhy there is so much resentment of Clinton, they
1. coreferent of entity 1
(previously known as
“Democrats”)
2. mention word will be
“they”
3. embedding of entity 1
will be updated
entity 1
entity 2
81. Entity Language Model
(Yangfeng Ji, Chenhao Tan, Sebastian Martschat,
Yejin Choi, N.A.S., EMNLP 2017)
When Democrats wonderwhy there is so much resentment of Clinton, they
entity 1
entity 2
82. Entity Language Model
(Yangfeng Ji, Chenhao Tan, Sebastian Martschat,
Yejin Choi, N.A.S., EMNLP 2017)
When Democrats wonderwhy there is so much resentment of Clinton, they don’t
1. not part of an entity
mention
2. “don’t”
entity 1
entity 2
83. 128
132
136
140
5-gram LM RNN LM entity
language
model
Perplexity on CoNLL 2012 test set. CoNLL 2012 coreference evaluation.
50
55
60
65
70
75
Martschat and
Strube (2015)
reranked with entity
LM
CoNLL MUC F1 B3 CEAF
25
35
45
55
65
75
always
new
shallow
features
Modi et
al. (2017)
entity LM human
Accuracy: InScript.
85. Bias in the Future?
• Linguistic scaffold tasks.
86. Bias in the Future?
• Linguistic scaffold tasks.
• Language is by and about people.
87. Bias in the Future?
• Linguistic scaffold tasks.
• Language is by and about people.
• NLP is needed when texts are costly to read.
88. Bias in the Future?
• Linguistic scaffold tasks.
• Language is by and about people.
• NLP is needed when texts are costly to read.
• Polyglot learning.