SlideShare a Scribd company logo
1 of 26
Graph Structure
・Use search graph in phrase-based model
・At weighted acyclic directed graph G < Ф,V,E,s,g,𝐴>
Ф : phrase pair sets
Ф=feature vector h(・)・weight 𝜔
V: vertex ≡ partial hypotheses
E:edges ≡ weight of route
E ⊆ V×V× Ф×A
A: weight sets
Graph Structure
• out(𝑣)= 𝑣 = 𝑒 ∈ 𝐸|tail(𝑒) : edge sets which go
out from vertex 𝑣
• in(𝑣) = 𝑣 = 𝑒 ∈ 𝐸|head(𝑒) : edge sets which
head to vertex 𝑣
->Phrase pairs are linked by <out(𝑣), in(𝑣)>
At figure 5.8, phrase pair <へ行った, I went to> is
linked by
out(𝑣) = <-----,0,<s>> and in(𝑣)=<--・・・,9,went to>
𝑣
𝑣
Graph Structure
• If Ѱ=(𝑒1, 𝑒1,…, 𝑒l): rout from start to any vertexs,
head(𝑒k)=tail(𝑒k+1), then
Source language phrase sets:
𝑘=1
𝑙
𝑓(∅(𝑒 𝑘)) ≡ 𝑓(Ѱ)
Target language phrase sets:
𝑒(∅ 𝑒1 ), … , 𝑒(∅ 𝑒𝑙 ≡ 𝑒(Ѱ)
Route weight: 𝜔(Ѱ)= 𝑘=1
𝑙
𝜔(𝑒 𝑘)
Graph Structure
• In Fig.5.8, for the route
-> the parallel of word sets of source language
「行った」「へ」「領事館」is
“He went to the consulate”
Start
<行った,He went>
<へ,to>
<領事館,
the consulate>
Semiring
• set R equipped with two binary operations
addition“ + ” and multiplication “ × ”
• Associative:
a+(b+c)=(a+b)+c, a×(b×c)=(a×b)×c
• Commutative: a+b=b+a
• Distributional: a×(b+c)=(a×b)+(a×c)
• Additive inverse, multiplicative inverse
0+a=a+0=a; 1×a=a×1=a; 0×a=a×0=0
are not defined
Semiring
• In Table 5.1, tropical semiring is used to solve
maximization problem for route weight in
decoder
A ⊕ ⊗ 𝟎 𝟏
Tropical 𝑅−∞
∞ max + ー∞ 0
Semiring
• In weight directed graph G, for a rout from
starting point to ending point of source
language input f is Ѱ= 𝑒1, 𝑒1,…, 𝑒l
• Score of Ѱ = product of partial routes
𝜔(Ѱ)=⊗ 𝑘=1 𝜔(𝑒 𝑘)
-> Problem which maximize this score is
max⊗𝜔(𝑒)= ⊕⊗𝜔(𝑒)
A ⊕ ⊗ 𝟎 𝟏
Tropical 𝑅−∞
∞ max + ー∞ 0
Semiring
• In Fig.5.7,line 11
Q(𝑣′
, 𝑗′′
+1,𝑒′
𝑠 𝑒′′
𝑠)←max
Q(𝑣′
, 𝑗′′
+1,𝑒′
𝑠 𝑒′′
𝑠),
Q(𝑣, 𝑗, 𝑒′
𝑒′′
)+𝑠 𝑑 + 𝑠∅ + 𝑠𝑙𝑚
additive operation ⊕ is implemented for
each vertex tail(e)=s of G
• As semiring sastifies distributional feature
-> weight 𝜔(𝑣)of any vertexs 𝑣 ∈V is
⊕⊗𝜔(𝑒)=⊕ 𝑒∈𝑖𝑛(𝑣) 𝜔(𝑒)⊗ 𝜔(𝑡𝑎𝑖𝑙(𝑒))
Semiring
• Forward-backward algorithm for finding
maximum of route weight in graph structure
• topological order(G): list of vertexs of graph G
which arranged in topological order
• 𝛼, 𝛽: external variable
Semiring
FORWARD(G)
• 𝑣 ∈ topological order(G), e∈in(𝑣)
𝜔 = 𝜔(𝑒)⊗ 𝛼(𝑡𝑎𝑖𝑙(𝑒))
𝛼 𝑣 = 𝛼(𝑣)⊕ 𝜔
Start
tail(e)
𝜔(e)
𝜔 = 𝜔(e) ⊗ 𝛼(𝑡𝑎𝑖𝑙(𝑒))
Semiring
BACKWARD(G)
• 𝑣 ∈ inversetopological order(G), e∈ out(𝑣)
𝜔 = 𝜔(𝑒)⊗ 𝛽(ℎ𝑒𝑎𝑑(𝑒))
𝛽 𝑣 = 𝛽(𝑣)⊕ 𝜔
Goal
𝜔(e)
𝜔 = 𝜔(e)⊗ 𝛽(ℎ𝑒𝑎𝑑(𝑒))
head(e)
Semiring
In problem which choose the optimum
translation from search space expressed by
weighted directed graph G
Tropical semiring + Forward algorithm
->Viterbi semiring
k-best
• Besides forward-backward algorithm, k-best
algorithm is used to optimize route weight
• Dijkstra’s algorithm: for single source shortest
path problem
• Eppstein’s algorithm: for heaping multiple paths
efficiently
k-best
• Assume problem satisfies Tropical semiring
and backward algorithm
• Calculate and choose max (weight 𝛽(𝑣))
• Fig.5.10 algorithm
・cand: priority queue
・< 𝑣, s>: partial route
・< 𝑣′
,𝑠′
>: partial route whose vertex 𝑣′
= 𝑣
and edge 𝑠′
= tail 𝑒 = 𝑒 ∈out(𝑣)
・D: set of < 𝑣′
,𝑠′
>
k-best
• k=1: Initialized cand
• Optimize weight of partial route and whole
route
Whole route
D
cand
optimal
get out < 𝑣, s>,register D
Choose 𝑣′ = 𝑣 and
𝑒′ = e ∈out(𝑣)
insert to cand
heap 𝛽(・) to get optimal
k time
Limitation of Search Space
• If search space is big
->any sort can be forgiven
->calculation amount of decode algorithm
become massive
->limitation is necessary:
・Distortion limit, constraint
・Reordering limit, constraint
Distortion Constraint
• Upper limit setting d for distance between
phrase pair ∅ 𝑘and∅ 𝑘−1: start 𝑘 − end 𝑘−1 ≤d
The purpose is making model score small if
model distorted lead to penalty become big
For language pair which do not have big sort,
distortion constraint reach good efficiency
If d=0: no skip, translate from left to right
smoothly
->monotone translation
Distortion Constraint
• Constraint for case when have partial phrases
do not reach the ending point
𝑗: position of the first phrase of source language
start 𝑘: the first position of translated phrase
If ( 𝑗 < start 𝑘), add
end 𝑘 − 𝑗 ≤d
・IBM Constraint
𝑗 𝑠𝑡𝑎𝑟𝑡 𝑘 𝑒𝑛𝑑 𝑘・・・
∅ 𝑘 phrase
No need to
exam
Beam Search
・Prune disused partial hypothesis and pay
attention only partial hypothesis with high score
for computational reduction
・Group of vertexs of search graph and prune
partial hypothesis which has low score
Beam Search
・Group of vertexs of search graph and prune
partial hypothesis which has low score
Partial hypothesis pruned Partial hypothesis chose
Beam Search
Some kinds of grouping:
- Cover vector grouping
- Radix grouping
- Beam width pruning
- Histogram pruning
Heuristic Function
• Prevent partial hypothesis which has not been
translated yet from pruning
• Give predicted score for the rout and learn by
A* search so that rout score get the maximum
• ->can reduce search error
Pre-reordering Method
Translation between languages which has
significantly different grammatical structure
• Pre-reordering rule
• Pre-reordering model
• Pre-reordering learning
Pre-reordering Rule
• Based on tree from syntactic analysis, reorder to
target language word order
• Head-driven phrase structure grammar(HPSG)’s
rule:
- Syntactic anlysis
- Move the subjects back
Pre-reordering Model
• Source languages must have syntactic analysis
tool and morphological analysis tool
• Bilingual data are necessary
• Probability value of pre-reordering patterns
obtained will be estimated by maximum-
likelihood estimation(MLE)
• Choose the suitable pre-reordering patterns
based on reordering part of speech from
morphological analysis, or clustering word
class
Pre-reordering Learning
• For language pairs without any syntactic
analysis tools and morphological analysis tools
• Provisional tree structure automatically
generated from syntactic analysis result
• Divide tree factors to 2 labels: reordering label
[X],and no-reordering label <X>
• Use linear ordering problem(LOP) to
formulate reordering model to find the
approximate solution and build the parse tree

More Related Content

What's hot

Algorithm Design and Complexity - Course 7
Algorithm Design and Complexity - Course 7Algorithm Design and Complexity - Course 7
Algorithm Design and Complexity - Course 7Traian Rebedea
 
REBAR: Low-variance, unbiased gradient estimates for discrete latent variable...
REBAR: Low-variance, unbiased gradient estimates for discrete latent variable...REBAR: Low-variance, unbiased gradient estimates for discrete latent variable...
REBAR: Low-variance, unbiased gradient estimates for discrete latent variable...Sangwoo Mo
 
Information in the Weights
Information in the WeightsInformation in the Weights
Information in the WeightsMark Chang
 
Information in the Weights
Information in the WeightsInformation in the Weights
Information in the WeightsMark Chang
 
Typing quantum superpositions and measurement
Typing quantum superpositions and measurementTyping quantum superpositions and measurement
Typing quantum superpositions and measurementAlejandro Díaz-Caro
 
Minimizing cost in distributed multiquery processing applications
Minimizing cost in distributed multiquery processing applicationsMinimizing cost in distributed multiquery processing applications
Minimizing cost in distributed multiquery processing applicationsLuis Galárraga
 
A new Perron-Frobenius theorem for nonnegative tensors
A new Perron-Frobenius theorem for nonnegative tensorsA new Perron-Frobenius theorem for nonnegative tensors
A new Perron-Frobenius theorem for nonnegative tensorsFrancesco Tudisco
 
Wei Yang - 2015 - Sampling-based Alignment and Hierarchical Sub-sentential Al...
Wei Yang - 2015 - Sampling-based Alignment and Hierarchical Sub-sentential Al...Wei Yang - 2015 - Sampling-based Alignment and Hierarchical Sub-sentential Al...
Wei Yang - 2015 - Sampling-based Alignment and Hierarchical Sub-sentential Al...Association for Computational Linguistics
 
140106 isaim-okayama
140106 isaim-okayama140106 isaim-okayama
140106 isaim-okayamagumitaro2012
 
On the Jensen-Shannon symmetrization of distances relying on abstract means
On the Jensen-Shannon symmetrization of distances relying on abstract meansOn the Jensen-Shannon symmetrization of distances relying on abstract means
On the Jensen-Shannon symmetrization of distances relying on abstract meansFrank Nielsen
 
Unit II Problem Solving Methods in AI K.sundar,AP/CSE,VEC
Unit II Problem Solving Methods in AI K.sundar,AP/CSE,VECUnit II Problem Solving Methods in AI K.sundar,AP/CSE,VEC
Unit II Problem Solving Methods in AI K.sundar,AP/CSE,VECsundarKanagaraj1
 
Nodal Domain Theorem for the p-Laplacian on Graphs and the Related Multiway C...
Nodal Domain Theorem for the p-Laplacian on Graphs and the Related Multiway C...Nodal Domain Theorem for the p-Laplacian on Graphs and the Related Multiway C...
Nodal Domain Theorem for the p-Laplacian on Graphs and the Related Multiway C...Francesco Tudisco
 
Paper introduction to Combinatorial Optimization on Graphs of Bounded Treewidth
Paper introduction to Combinatorial Optimization on Graphs of Bounded TreewidthPaper introduction to Combinatorial Optimization on Graphs of Bounded Treewidth
Paper introduction to Combinatorial Optimization on Graphs of Bounded TreewidthYu Liu
 
Refining Bayesian Data Analysis Methods for Use with Longer Waveforms
Refining Bayesian Data Analysis Methods for Use with Longer WaveformsRefining Bayesian Data Analysis Methods for Use with Longer Waveforms
Refining Bayesian Data Analysis Methods for Use with Longer WaveformsJames Bell
 

What's hot (19)

Algorithm Design and Complexity - Course 7
Algorithm Design and Complexity - Course 7Algorithm Design and Complexity - Course 7
Algorithm Design and Complexity - Course 7
 
REBAR: Low-variance, unbiased gradient estimates for discrete latent variable...
REBAR: Low-variance, unbiased gradient estimates for discrete latent variable...REBAR: Low-variance, unbiased gradient estimates for discrete latent variable...
REBAR: Low-variance, unbiased gradient estimates for discrete latent variable...
 
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
 
Information in the Weights
Information in the WeightsInformation in the Weights
Information in the Weights
 
Information in the Weights
Information in the WeightsInformation in the Weights
Information in the Weights
 
Typing quantum superpositions and measurement
Typing quantum superpositions and measurementTyping quantum superpositions and measurement
Typing quantum superpositions and measurement
 
Minimizing cost in distributed multiquery processing applications
Minimizing cost in distributed multiquery processing applicationsMinimizing cost in distributed multiquery processing applications
Minimizing cost in distributed multiquery processing applications
 
A new Perron-Frobenius theorem for nonnegative tensors
A new Perron-Frobenius theorem for nonnegative tensorsA new Perron-Frobenius theorem for nonnegative tensors
A new Perron-Frobenius theorem for nonnegative tensors
 
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
 
Sets in discrete mathematics
Sets in discrete mathematicsSets in discrete mathematics
Sets in discrete mathematics
 
Wei Yang - 2015 - Sampling-based Alignment and Hierarchical Sub-sentential Al...
Wei Yang - 2015 - Sampling-based Alignment and Hierarchical Sub-sentential Al...Wei Yang - 2015 - Sampling-based Alignment and Hierarchical Sub-sentential Al...
Wei Yang - 2015 - Sampling-based Alignment and Hierarchical Sub-sentential Al...
 
140106 isaim-okayama
140106 isaim-okayama140106 isaim-okayama
140106 isaim-okayama
 
Link analysis
Link analysisLink analysis
Link analysis
 
Presentation
PresentationPresentation
Presentation
 
On the Jensen-Shannon symmetrization of distances relying on abstract means
On the Jensen-Shannon symmetrization of distances relying on abstract meansOn the Jensen-Shannon symmetrization of distances relying on abstract means
On the Jensen-Shannon symmetrization of distances relying on abstract means
 
Unit II Problem Solving Methods in AI K.sundar,AP/CSE,VEC
Unit II Problem Solving Methods in AI K.sundar,AP/CSE,VECUnit II Problem Solving Methods in AI K.sundar,AP/CSE,VEC
Unit II Problem Solving Methods in AI K.sundar,AP/CSE,VEC
 
Nodal Domain Theorem for the p-Laplacian on Graphs and the Related Multiway C...
Nodal Domain Theorem for the p-Laplacian on Graphs and the Related Multiway C...Nodal Domain Theorem for the p-Laplacian on Graphs and the Related Multiway C...
Nodal Domain Theorem for the p-Laplacian on Graphs and the Related Multiway C...
 
Paper introduction to Combinatorial Optimization on Graphs of Bounded Treewidth
Paper introduction to Combinatorial Optimization on Graphs of Bounded TreewidthPaper introduction to Combinatorial Optimization on Graphs of Bounded Treewidth
Paper introduction to Combinatorial Optimization on Graphs of Bounded Treewidth
 
Refining Bayesian Data Analysis Methods for Use with Longer Waveforms
Refining Bayesian Data Analysis Methods for Use with Longer WaveformsRefining Bayesian Data Analysis Methods for Use with Longer Waveforms
Refining Bayesian Data Analysis Methods for Use with Longer Waveforms
 

Viewers also liked

[Paper Introduction] Supervised Phrase Table Triangulation with Neural Word E...
[Paper Introduction] Supervised Phrase Table Triangulation with Neural Word E...[Paper Introduction] Supervised Phrase Table Triangulation with Neural Word E...
[Paper Introduction] Supervised Phrase Table Triangulation with Neural Word E...NAIST Machine Translation Study Group
 
[Paper Introduction] Bilingual word representations with monolingual quality ...
[Paper Introduction] Bilingual word representations with monolingual quality ...[Paper Introduction] Bilingual word representations with monolingual quality ...
[Paper Introduction] Bilingual word representations with monolingual quality ...NAIST Machine Translation Study Group
 
[Paper Introduction] Evaluating MT Systems with Second Language Proficiency T...
[Paper Introduction] Evaluating MT Systems with Second Language Proficiency T...[Paper Introduction] Evaluating MT Systems with Second Language Proficiency T...
[Paper Introduction] Evaluating MT Systems with Second Language Proficiency T...NAIST Machine Translation Study Group
 
[Paper Introduction] Translating into Morphologically Rich Languages with Syn...
[Paper Introduction] Translating into Morphologically Rich Languages with Syn...[Paper Introduction] Translating into Morphologically Rich Languages with Syn...
[Paper Introduction] Translating into Morphologically Rich Languages with Syn...NAIST Machine Translation Study Group
 
[Paper Introduction] Training a Natural Language Generator From Unaligned Data
[Paper Introduction] Training a Natural Language Generator From Unaligned Data[Paper Introduction] Training a Natural Language Generator From Unaligned Data
[Paper Introduction] Training a Natural Language Generator From Unaligned DataNAIST Machine Translation Study Group
 
[Paper Introduction] Efficient top down btg parsing for machine translation p...
[Paper Introduction] Efficient top down btg parsing for machine translation p...[Paper Introduction] Efficient top down btg parsing for machine translation p...
[Paper Introduction] Efficient top down btg parsing for machine translation p...NAIST Machine Translation Study Group
 
[Paper Introduction] A Context-Aware Topic Model for Statistical Machine Tran...
[Paper Introduction] A Context-Aware Topic Model for Statistical Machine Tran...[Paper Introduction] A Context-Aware Topic Model for Statistical Machine Tran...
[Paper Introduction] A Context-Aware Topic Model for Statistical Machine Tran...NAIST Machine Translation Study Group
 
Diffuser soi-même sa recherche: quelques outils et stratégies pour l'étudiant...
Diffuser soi-même sa recherche: quelques outils et stratégies pour l'étudiant...Diffuser soi-même sa recherche: quelques outils et stratégies pour l'étudiant...
Diffuser soi-même sa recherche: quelques outils et stratégies pour l'étudiant...Gabriel Dumouchel, Ph.D.
 
La présence numérique de l'étudiant-chercheur en éducation: quelques outils p...
La présence numérique de l'étudiant-chercheur en éducation: quelques outils p...La présence numérique de l'étudiant-chercheur en éducation: quelques outils p...
La présence numérique de l'étudiant-chercheur en éducation: quelques outils p...Gabriel Dumouchel, Ph.D.
 
Zotero Standalone : un incontournable pour gérer vos références de recher...
Zotero Standalone : un incontournable pour gérer vos références de recher...Zotero Standalone : un incontournable pour gérer vos références de recher...
Zotero Standalone : un incontournable pour gérer vos références de recher...Gabriel Dumouchel, Ph.D.
 
LEGRIS Presentation
LEGRIS PresentationLEGRIS Presentation
LEGRIS PresentationBruno Binet
 
PARKER Presentation
PARKER PresentationPARKER Presentation
PARKER PresentationBruno Binet
 
Comment gérer son identité numérique de chercheur ou d’étudiant-chercheur en ...
Comment gérer son identité numérique de chercheur ou d’étudiant-chercheur en ...Comment gérer son identité numérique de chercheur ou d’étudiant-chercheur en ...
Comment gérer son identité numérique de chercheur ou d’étudiant-chercheur en ...Gabriel Dumouchel, Ph.D.
 
La promotion de l’identité numérique des chercheurs et des étudiants-cherc...
La promotion de l’identité numérique des chercheurs et des étudiants-cherc...La promotion de l’identité numérique des chercheurs et des étudiants-cherc...
La promotion de l’identité numérique des chercheurs et des étudiants-cherc...Gabriel Dumouchel, Ph.D.
 

Viewers also liked (20)

[Book Reading] 機械翻訳 - Section 7 No.1
[Book Reading] 機械翻訳 - Section 7 No.1[Book Reading] 機械翻訳 - Section 7 No.1
[Book Reading] 機械翻訳 - Section 7 No.1
 
Henk de Vries
Henk de VriesHenk de Vries
Henk de Vries
 
MBYRussia
MBYRussiaMBYRussia
MBYRussia
 
[Book Reading] 機械翻訳 - Section 3 No.1
[Book Reading] 機械翻訳 - Section 3 No.1[Book Reading] 機械翻訳 - Section 3 No.1
[Book Reading] 機械翻訳 - Section 3 No.1
 
[Paper Introduction] Supervised Phrase Table Triangulation with Neural Word E...
[Paper Introduction] Supervised Phrase Table Triangulation with Neural Word E...[Paper Introduction] Supervised Phrase Table Triangulation with Neural Word E...
[Paper Introduction] Supervised Phrase Table Triangulation with Neural Word E...
 
[Paper Introduction] Bilingual word representations with monolingual quality ...
[Paper Introduction] Bilingual word representations with monolingual quality ...[Paper Introduction] Bilingual word representations with monolingual quality ...
[Paper Introduction] Bilingual word representations with monolingual quality ...
 
[Paper Introduction] Evaluating MT Systems with Second Language Proficiency T...
[Paper Introduction] Evaluating MT Systems with Second Language Proficiency T...[Paper Introduction] Evaluating MT Systems with Second Language Proficiency T...
[Paper Introduction] Evaluating MT Systems with Second Language Proficiency T...
 
[Book Reading] 機械翻訳 - Section 2 No.2
 [Book Reading] 機械翻訳 - Section 2 No.2 [Book Reading] 機械翻訳 - Section 2 No.2
[Book Reading] 機械翻訳 - Section 2 No.2
 
[Paper Introduction] Translating into Morphologically Rich Languages with Syn...
[Paper Introduction] Translating into Morphologically Rich Languages with Syn...[Paper Introduction] Translating into Morphologically Rich Languages with Syn...
[Paper Introduction] Translating into Morphologically Rich Languages with Syn...
 
[Paper Introduction] Training a Natural Language Generator From Unaligned Data
[Paper Introduction] Training a Natural Language Generator From Unaligned Data[Paper Introduction] Training a Natural Language Generator From Unaligned Data
[Paper Introduction] Training a Natural Language Generator From Unaligned Data
 
[Paper Introduction] Efficient top down btg parsing for machine translation p...
[Paper Introduction] Efficient top down btg parsing for machine translation p...[Paper Introduction] Efficient top down btg parsing for machine translation p...
[Paper Introduction] Efficient top down btg parsing for machine translation p...
 
TCR 20 Sharkwater
TCR 20 SharkwaterTCR 20 Sharkwater
TCR 20 Sharkwater
 
[Paper Introduction] A Context-Aware Topic Model for Statistical Machine Tran...
[Paper Introduction] A Context-Aware Topic Model for Statistical Machine Tran...[Paper Introduction] A Context-Aware Topic Model for Statistical Machine Tran...
[Paper Introduction] A Context-Aware Topic Model for Statistical Machine Tran...
 
Diffuser soi-même sa recherche: quelques outils et stratégies pour l'étudiant...
Diffuser soi-même sa recherche: quelques outils et stratégies pour l'étudiant...Diffuser soi-même sa recherche: quelques outils et stratégies pour l'étudiant...
Diffuser soi-même sa recherche: quelques outils et stratégies pour l'étudiant...
 
La présence numérique de l'étudiant-chercheur en éducation: quelques outils p...
La présence numérique de l'étudiant-chercheur en éducation: quelques outils p...La présence numérique de l'étudiant-chercheur en éducation: quelques outils p...
La présence numérique de l'étudiant-chercheur en éducation: quelques outils p...
 
Zotero Standalone : un incontournable pour gérer vos références de recher...
Zotero Standalone : un incontournable pour gérer vos références de recher...Zotero Standalone : un incontournable pour gérer vos références de recher...
Zotero Standalone : un incontournable pour gérer vos références de recher...
 
LEGRIS Presentation
LEGRIS PresentationLEGRIS Presentation
LEGRIS Presentation
 
PARKER Presentation
PARKER PresentationPARKER Presentation
PARKER Presentation
 
Comment gérer son identité numérique de chercheur ou d’étudiant-chercheur en ...
Comment gérer son identité numérique de chercheur ou d’étudiant-chercheur en ...Comment gérer son identité numérique de chercheur ou d’étudiant-chercheur en ...
Comment gérer son identité numérique de chercheur ou d’étudiant-chercheur en ...
 
La promotion de l’identité numérique des chercheurs et des étudiants-cherc...
La promotion de l’identité numérique des chercheurs et des étudiants-cherc...La promotion de l’identité numérique des chercheurs et des étudiants-cherc...
La promotion de l’identité numérique des chercheurs et des étudiants-cherc...
 

Similar to [Book Reading] 機械翻訳 - Section 5 No.2

Future features for openCypher: Schema, Constraints, Subqueries, Configurable...
Future features for openCypher: Schema, Constraints, Subqueries, Configurable...Future features for openCypher: Schema, Constraints, Subqueries, Configurable...
Future features for openCypher: Schema, Constraints, Subqueries, Configurable...openCypher
 
G6 m5-b-lesson 7-t
G6 m5-b-lesson 7-tG6 m5-b-lesson 7-t
G6 m5-b-lesson 7-tmlabuski
 
Paper study: Attention, learn to solve routing problems!
Paper study: Attention, learn to solve routing problems!Paper study: Attention, learn to solve routing problems!
Paper study: Attention, learn to solve routing problems!ChenYiHuang5
 
Metrics for generativemodels
Metrics for generativemodelsMetrics for generativemodels
Metrics for generativemodelsDai-Hai Nguyen
 
Approximate Nearest Neighbour in Higher Dimensions
Approximate Nearest Neighbour in Higher DimensionsApproximate Nearest Neighbour in Higher Dimensions
Approximate Nearest Neighbour in Higher DimensionsShrey Verma
 
Optimum Engineering Design - Day 2b. Classical Optimization methods
Optimum Engineering Design - Day 2b. Classical Optimization methodsOptimum Engineering Design - Day 2b. Classical Optimization methods
Optimum Engineering Design - Day 2b. Classical Optimization methodsSantiagoGarridoBulln
 
lecture 17
lecture 17lecture 17
lecture 17sajinsc
 
Prestation_ClydeShen
Prestation_ClydeShenPrestation_ClydeShen
Prestation_ClydeShenClyde Shen
 
Algorithm to count number of disjoint paths
Algorithm to count number of disjoint pathsAlgorithm to count number of disjoint paths
Algorithm to count number of disjoint pathsSujith Jay Nair
 
is anyone_interest_in_auto-encoding_variational-bayes
is anyone_interest_in_auto-encoding_variational-bayesis anyone_interest_in_auto-encoding_variational-bayes
is anyone_interest_in_auto-encoding_variational-bayesNAVER Engineering
 
Vehicle Routing Problem using PSO (Particle Swarm Optimization)
Vehicle Routing Problem using PSO (Particle Swarm Optimization)Vehicle Routing Problem using PSO (Particle Swarm Optimization)
Vehicle Routing Problem using PSO (Particle Swarm Optimization)Niharika Varshney
 
Paper Study: Melding the data decision pipeline
Paper Study: Melding the data decision pipelinePaper Study: Melding the data decision pipeline
Paper Study: Melding the data decision pipelineChenYiHuang5
 
Secure Domination in graphs
Secure Domination in graphsSecure Domination in graphs
Secure Domination in graphsMahesh Gadhwal
 
openCypher: Further Developments on Path Pattern Queries (Regular Path Queries)
openCypher: Further Developments on Path Pattern Queries (Regular Path Queries)openCypher: Further Developments on Path Pattern Queries (Regular Path Queries)
openCypher: Further Developments on Path Pattern Queries (Regular Path Queries)openCypher
 
Single source shortes path in dag
Single source shortes path in dagSingle source shortes path in dag
Single source shortes path in dagKiran K
 
DFA minimization algorithms in map reduce
DFA minimization algorithms in map reduceDFA minimization algorithms in map reduce
DFA minimization algorithms in map reduceIraj Hedayati
 
20180831 riemannian representation learning
20180831 riemannian representation learning20180831 riemannian representation learning
20180831 riemannian representation learningsegwangkim
 

Similar to [Book Reading] 機械翻訳 - Section 5 No.2 (20)

Future features for openCypher: Schema, Constraints, Subqueries, Configurable...
Future features for openCypher: Schema, Constraints, Subqueries, Configurable...Future features for openCypher: Schema, Constraints, Subqueries, Configurable...
Future features for openCypher: Schema, Constraints, Subqueries, Configurable...
 
G6 m5-b-lesson 7-t
G6 m5-b-lesson 7-tG6 m5-b-lesson 7-t
G6 m5-b-lesson 7-t
 
Paper study: Attention, learn to solve routing problems!
Paper study: Attention, learn to solve routing problems!Paper study: Attention, learn to solve routing problems!
Paper study: Attention, learn to solve routing problems!
 
Metrics for generativemodels
Metrics for generativemodelsMetrics for generativemodels
Metrics for generativemodels
 
Approximate Nearest Neighbour in Higher Dimensions
Approximate Nearest Neighbour in Higher DimensionsApproximate Nearest Neighbour in Higher Dimensions
Approximate Nearest Neighbour in Higher Dimensions
 
Optimum Engineering Design - Day 2b. Classical Optimization methods
Optimum Engineering Design - Day 2b. Classical Optimization methodsOptimum Engineering Design - Day 2b. Classical Optimization methods
Optimum Engineering Design - Day 2b. Classical Optimization methods
 
Biological sequences analysis
Biological sequences analysisBiological sequences analysis
Biological sequences analysis
 
lecture 17
lecture 17lecture 17
lecture 17
 
Prestation_ClydeShen
Prestation_ClydeShenPrestation_ClydeShen
Prestation_ClydeShen
 
Lash
LashLash
Lash
 
Algorithm to count number of disjoint paths
Algorithm to count number of disjoint pathsAlgorithm to count number of disjoint paths
Algorithm to count number of disjoint paths
 
is anyone_interest_in_auto-encoding_variational-bayes
is anyone_interest_in_auto-encoding_variational-bayesis anyone_interest_in_auto-encoding_variational-bayes
is anyone_interest_in_auto-encoding_variational-bayes
 
Vehicle Routing Problem using PSO (Particle Swarm Optimization)
Vehicle Routing Problem using PSO (Particle Swarm Optimization)Vehicle Routing Problem using PSO (Particle Swarm Optimization)
Vehicle Routing Problem using PSO (Particle Swarm Optimization)
 
Paper Study: Melding the data decision pipeline
Paper Study: Melding the data decision pipelinePaper Study: Melding the data decision pipeline
Paper Study: Melding the data decision pipeline
 
Secure Domination in graphs
Secure Domination in graphsSecure Domination in graphs
Secure Domination in graphs
 
02-alignment.pdf
02-alignment.pdf02-alignment.pdf
02-alignment.pdf
 
openCypher: Further Developments on Path Pattern Queries (Regular Path Queries)
openCypher: Further Developments on Path Pattern Queries (Regular Path Queries)openCypher: Further Developments on Path Pattern Queries (Regular Path Queries)
openCypher: Further Developments on Path Pattern Queries (Regular Path Queries)
 
Single source shortes path in dag
Single source shortes path in dagSingle source shortes path in dag
Single source shortes path in dag
 
DFA minimization algorithms in map reduce
DFA minimization algorithms in map reduceDFA minimization algorithms in map reduce
DFA minimization algorithms in map reduce
 
20180831 riemannian representation learning
20180831 riemannian representation learning20180831 riemannian representation learning
20180831 riemannian representation learning
 

Recently uploaded

VVIP Call Girls Nalasopara : 9892124323, Call Girls in Nalasopara Services
VVIP Call Girls Nalasopara : 9892124323, Call Girls in Nalasopara ServicesVVIP Call Girls Nalasopara : 9892124323, Call Girls in Nalasopara Services
VVIP Call Girls Nalasopara : 9892124323, Call Girls in Nalasopara ServicesPooja Nehwal
 
Mohammad_Alnahdi_Oral_Presentation_Assignment.pptx
Mohammad_Alnahdi_Oral_Presentation_Assignment.pptxMohammad_Alnahdi_Oral_Presentation_Assignment.pptx
Mohammad_Alnahdi_Oral_Presentation_Assignment.pptxmohammadalnahdi22
 
WhatsApp 📞 9892124323 ✅Call Girls In Juhu ( Mumbai )
WhatsApp 📞 9892124323 ✅Call Girls In Juhu ( Mumbai )WhatsApp 📞 9892124323 ✅Call Girls In Juhu ( Mumbai )
WhatsApp 📞 9892124323 ✅Call Girls In Juhu ( Mumbai )Pooja Nehwal
 
Andrés Ramírez Gossler, Facundo Schinnea - eCommerce Day Chile 2024
Andrés Ramírez Gossler, Facundo Schinnea - eCommerce Day Chile 2024Andrés Ramírez Gossler, Facundo Schinnea - eCommerce Day Chile 2024
Andrés Ramírez Gossler, Facundo Schinnea - eCommerce Day Chile 2024eCommerce Institute
 
Microsoft Copilot AI for Everyone - created by AI
Microsoft Copilot AI for Everyone - created by AIMicrosoft Copilot AI for Everyone - created by AI
Microsoft Copilot AI for Everyone - created by AITatiana Gurgel
 
If this Giant Must Walk: A Manifesto for a New Nigeria
If this Giant Must Walk: A Manifesto for a New NigeriaIf this Giant Must Walk: A Manifesto for a New Nigeria
If this Giant Must Walk: A Manifesto for a New NigeriaKayode Fayemi
 
Re-membering the Bard: Revisiting The Compleat Wrks of Wllm Shkspr (Abridged)...
Re-membering the Bard: Revisiting The Compleat Wrks of Wllm Shkspr (Abridged)...Re-membering the Bard: Revisiting The Compleat Wrks of Wllm Shkspr (Abridged)...
Re-membering the Bard: Revisiting The Compleat Wrks of Wllm Shkspr (Abridged)...Hasting Chen
 
Night 7k Call Girls Noida Sector 128 Call Me: 8448380779
Night 7k Call Girls Noida Sector 128 Call Me: 8448380779Night 7k Call Girls Noida Sector 128 Call Me: 8448380779
Night 7k Call Girls Noida Sector 128 Call Me: 8448380779Delhi Call girls
 
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...Sheetaleventcompany
 
Navi Mumbai Call Girls Service Pooja 9892124323 Real Russian Girls Looking Mo...
Navi Mumbai Call Girls Service Pooja 9892124323 Real Russian Girls Looking Mo...Navi Mumbai Call Girls Service Pooja 9892124323 Real Russian Girls Looking Mo...
Navi Mumbai Call Girls Service Pooja 9892124323 Real Russian Girls Looking Mo...Pooja Nehwal
 
BDSM⚡Call Girls in Sector 93 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 93 Noida Escorts >༒8448380779 Escort ServiceBDSM⚡Call Girls in Sector 93 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 93 Noida Escorts >༒8448380779 Escort ServiceDelhi Call girls
 
SaaStr Workshop Wednesday w/ Lucas Price, Yardstick
SaaStr Workshop Wednesday w/ Lucas Price, YardstickSaaStr Workshop Wednesday w/ Lucas Price, Yardstick
SaaStr Workshop Wednesday w/ Lucas Price, Yardsticksaastr
 
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptx
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptxChiulli_Aurora_Oman_Raffaele_Beowulf.pptx
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptxraffaeleoman
 
CTAC 2024 Valencia - Henrik Hanke - Reduce to the max - slideshare.pdf
CTAC 2024 Valencia - Henrik Hanke - Reduce to the max - slideshare.pdfCTAC 2024 Valencia - Henrik Hanke - Reduce to the max - slideshare.pdf
CTAC 2024 Valencia - Henrik Hanke - Reduce to the max - slideshare.pdfhenrik385807
 
Mathematics of Finance Presentation.pptx
Mathematics of Finance Presentation.pptxMathematics of Finance Presentation.pptx
Mathematics of Finance Presentation.pptxMoumonDas2
 
Governance and Nation-Building in Nigeria: Some Reflections on Options for Po...
Governance and Nation-Building in Nigeria: Some Reflections on Options for Po...Governance and Nation-Building in Nigeria: Some Reflections on Options for Po...
Governance and Nation-Building in Nigeria: Some Reflections on Options for Po...Kayode Fayemi
 
CTAC 2024 Valencia - Sven Zoelle - Most Crucial Invest to Digitalisation_slid...
CTAC 2024 Valencia - Sven Zoelle - Most Crucial Invest to Digitalisation_slid...CTAC 2024 Valencia - Sven Zoelle - Most Crucial Invest to Digitalisation_slid...
CTAC 2024 Valencia - Sven Zoelle - Most Crucial Invest to Digitalisation_slid...henrik385807
 
George Lever - eCommerce Day Chile 2024
George Lever -  eCommerce Day Chile 2024George Lever -  eCommerce Day Chile 2024
George Lever - eCommerce Day Chile 2024eCommerce Institute
 
Presentation on Engagement in Book Clubs
Presentation on Engagement in Book ClubsPresentation on Engagement in Book Clubs
Presentation on Engagement in Book Clubssamaasim06
 
Thirunelveli call girls Tamil escorts 7877702510
Thirunelveli call girls Tamil escorts 7877702510Thirunelveli call girls Tamil escorts 7877702510
Thirunelveli call girls Tamil escorts 7877702510Vipesco
 

Recently uploaded (20)

VVIP Call Girls Nalasopara : 9892124323, Call Girls in Nalasopara Services
VVIP Call Girls Nalasopara : 9892124323, Call Girls in Nalasopara ServicesVVIP Call Girls Nalasopara : 9892124323, Call Girls in Nalasopara Services
VVIP Call Girls Nalasopara : 9892124323, Call Girls in Nalasopara Services
 
Mohammad_Alnahdi_Oral_Presentation_Assignment.pptx
Mohammad_Alnahdi_Oral_Presentation_Assignment.pptxMohammad_Alnahdi_Oral_Presentation_Assignment.pptx
Mohammad_Alnahdi_Oral_Presentation_Assignment.pptx
 
WhatsApp 📞 9892124323 ✅Call Girls In Juhu ( Mumbai )
WhatsApp 📞 9892124323 ✅Call Girls In Juhu ( Mumbai )WhatsApp 📞 9892124323 ✅Call Girls In Juhu ( Mumbai )
WhatsApp 📞 9892124323 ✅Call Girls In Juhu ( Mumbai )
 
Andrés Ramírez Gossler, Facundo Schinnea - eCommerce Day Chile 2024
Andrés Ramírez Gossler, Facundo Schinnea - eCommerce Day Chile 2024Andrés Ramírez Gossler, Facundo Schinnea - eCommerce Day Chile 2024
Andrés Ramírez Gossler, Facundo Schinnea - eCommerce Day Chile 2024
 
Microsoft Copilot AI for Everyone - created by AI
Microsoft Copilot AI for Everyone - created by AIMicrosoft Copilot AI for Everyone - created by AI
Microsoft Copilot AI for Everyone - created by AI
 
If this Giant Must Walk: A Manifesto for a New Nigeria
If this Giant Must Walk: A Manifesto for a New NigeriaIf this Giant Must Walk: A Manifesto for a New Nigeria
If this Giant Must Walk: A Manifesto for a New Nigeria
 
Re-membering the Bard: Revisiting The Compleat Wrks of Wllm Shkspr (Abridged)...
Re-membering the Bard: Revisiting The Compleat Wrks of Wllm Shkspr (Abridged)...Re-membering the Bard: Revisiting The Compleat Wrks of Wllm Shkspr (Abridged)...
Re-membering the Bard: Revisiting The Compleat Wrks of Wllm Shkspr (Abridged)...
 
Night 7k Call Girls Noida Sector 128 Call Me: 8448380779
Night 7k Call Girls Noida Sector 128 Call Me: 8448380779Night 7k Call Girls Noida Sector 128 Call Me: 8448380779
Night 7k Call Girls Noida Sector 128 Call Me: 8448380779
 
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...
 
Navi Mumbai Call Girls Service Pooja 9892124323 Real Russian Girls Looking Mo...
Navi Mumbai Call Girls Service Pooja 9892124323 Real Russian Girls Looking Mo...Navi Mumbai Call Girls Service Pooja 9892124323 Real Russian Girls Looking Mo...
Navi Mumbai Call Girls Service Pooja 9892124323 Real Russian Girls Looking Mo...
 
BDSM⚡Call Girls in Sector 93 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 93 Noida Escorts >༒8448380779 Escort ServiceBDSM⚡Call Girls in Sector 93 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 93 Noida Escorts >༒8448380779 Escort Service
 
SaaStr Workshop Wednesday w/ Lucas Price, Yardstick
SaaStr Workshop Wednesday w/ Lucas Price, YardstickSaaStr Workshop Wednesday w/ Lucas Price, Yardstick
SaaStr Workshop Wednesday w/ Lucas Price, Yardstick
 
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptx
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptxChiulli_Aurora_Oman_Raffaele_Beowulf.pptx
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptx
 
CTAC 2024 Valencia - Henrik Hanke - Reduce to the max - slideshare.pdf
CTAC 2024 Valencia - Henrik Hanke - Reduce to the max - slideshare.pdfCTAC 2024 Valencia - Henrik Hanke - Reduce to the max - slideshare.pdf
CTAC 2024 Valencia - Henrik Hanke - Reduce to the max - slideshare.pdf
 
Mathematics of Finance Presentation.pptx
Mathematics of Finance Presentation.pptxMathematics of Finance Presentation.pptx
Mathematics of Finance Presentation.pptx
 
Governance and Nation-Building in Nigeria: Some Reflections on Options for Po...
Governance and Nation-Building in Nigeria: Some Reflections on Options for Po...Governance and Nation-Building in Nigeria: Some Reflections on Options for Po...
Governance and Nation-Building in Nigeria: Some Reflections on Options for Po...
 
CTAC 2024 Valencia - Sven Zoelle - Most Crucial Invest to Digitalisation_slid...
CTAC 2024 Valencia - Sven Zoelle - Most Crucial Invest to Digitalisation_slid...CTAC 2024 Valencia - Sven Zoelle - Most Crucial Invest to Digitalisation_slid...
CTAC 2024 Valencia - Sven Zoelle - Most Crucial Invest to Digitalisation_slid...
 
George Lever - eCommerce Day Chile 2024
George Lever -  eCommerce Day Chile 2024George Lever -  eCommerce Day Chile 2024
George Lever - eCommerce Day Chile 2024
 
Presentation on Engagement in Book Clubs
Presentation on Engagement in Book ClubsPresentation on Engagement in Book Clubs
Presentation on Engagement in Book Clubs
 
Thirunelveli call girls Tamil escorts 7877702510
Thirunelveli call girls Tamil escorts 7877702510Thirunelveli call girls Tamil escorts 7877702510
Thirunelveli call girls Tamil escorts 7877702510
 

[Book Reading] 機械翻訳 - Section 5 No.2

  • 1. Graph Structure ・Use search graph in phrase-based model ・At weighted acyclic directed graph G < Ф,V,E,s,g,𝐴> Ф : phrase pair sets Ф=feature vector h(・)・weight 𝜔 V: vertex ≡ partial hypotheses E:edges ≡ weight of route E ⊆ V×V× Ф×A A: weight sets
  • 2. Graph Structure • out(𝑣)= 𝑣 = 𝑒 ∈ 𝐸|tail(𝑒) : edge sets which go out from vertex 𝑣 • in(𝑣) = 𝑣 = 𝑒 ∈ 𝐸|head(𝑒) : edge sets which head to vertex 𝑣 ->Phrase pairs are linked by <out(𝑣), in(𝑣)> At figure 5.8, phrase pair <へ行った, I went to> is linked by out(𝑣) = <-----,0,<s>> and in(𝑣)=<--・・・,9,went to> 𝑣 𝑣
  • 3. Graph Structure • If Ѱ=(𝑒1, 𝑒1,…, 𝑒l): rout from start to any vertexs, head(𝑒k)=tail(𝑒k+1), then Source language phrase sets: 𝑘=1 𝑙 𝑓(∅(𝑒 𝑘)) ≡ 𝑓(Ѱ) Target language phrase sets: 𝑒(∅ 𝑒1 ), … , 𝑒(∅ 𝑒𝑙 ≡ 𝑒(Ѱ) Route weight: 𝜔(Ѱ)= 𝑘=1 𝑙 𝜔(𝑒 𝑘)
  • 4. Graph Structure • In Fig.5.8, for the route -> the parallel of word sets of source language 「行った」「へ」「領事館」is “He went to the consulate” Start <行った,He went> <へ,to> <領事館, the consulate>
  • 5. Semiring • set R equipped with two binary operations addition“ + ” and multiplication “ × ” • Associative: a+(b+c)=(a+b)+c, a×(b×c)=(a×b)×c • Commutative: a+b=b+a • Distributional: a×(b+c)=(a×b)+(a×c) • Additive inverse, multiplicative inverse 0+a=a+0=a; 1×a=a×1=a; 0×a=a×0=0 are not defined
  • 6. Semiring • In Table 5.1, tropical semiring is used to solve maximization problem for route weight in decoder A ⊕ ⊗ 𝟎 𝟏 Tropical 𝑅−∞ ∞ max + ー∞ 0
  • 7. Semiring • In weight directed graph G, for a rout from starting point to ending point of source language input f is Ѱ= 𝑒1, 𝑒1,…, 𝑒l • Score of Ѱ = product of partial routes 𝜔(Ѱ)=⊗ 𝑘=1 𝜔(𝑒 𝑘) -> Problem which maximize this score is max⊗𝜔(𝑒)= ⊕⊗𝜔(𝑒) A ⊕ ⊗ 𝟎 𝟏 Tropical 𝑅−∞ ∞ max + ー∞ 0
  • 8. Semiring • In Fig.5.7,line 11 Q(𝑣′ , 𝑗′′ +1,𝑒′ 𝑠 𝑒′′ 𝑠)←max Q(𝑣′ , 𝑗′′ +1,𝑒′ 𝑠 𝑒′′ 𝑠), Q(𝑣, 𝑗, 𝑒′ 𝑒′′ )+𝑠 𝑑 + 𝑠∅ + 𝑠𝑙𝑚 additive operation ⊕ is implemented for each vertex tail(e)=s of G • As semiring sastifies distributional feature -> weight 𝜔(𝑣)of any vertexs 𝑣 ∈V is ⊕⊗𝜔(𝑒)=⊕ 𝑒∈𝑖𝑛(𝑣) 𝜔(𝑒)⊗ 𝜔(𝑡𝑎𝑖𝑙(𝑒))
  • 9. Semiring • Forward-backward algorithm for finding maximum of route weight in graph structure • topological order(G): list of vertexs of graph G which arranged in topological order • 𝛼, 𝛽: external variable
  • 10. Semiring FORWARD(G) • 𝑣 ∈ topological order(G), e∈in(𝑣) 𝜔 = 𝜔(𝑒)⊗ 𝛼(𝑡𝑎𝑖𝑙(𝑒)) 𝛼 𝑣 = 𝛼(𝑣)⊕ 𝜔 Start tail(e) 𝜔(e) 𝜔 = 𝜔(e) ⊗ 𝛼(𝑡𝑎𝑖𝑙(𝑒))
  • 11. Semiring BACKWARD(G) • 𝑣 ∈ inversetopological order(G), e∈ out(𝑣) 𝜔 = 𝜔(𝑒)⊗ 𝛽(ℎ𝑒𝑎𝑑(𝑒)) 𝛽 𝑣 = 𝛽(𝑣)⊕ 𝜔 Goal 𝜔(e) 𝜔 = 𝜔(e)⊗ 𝛽(ℎ𝑒𝑎𝑑(𝑒)) head(e)
  • 12. Semiring In problem which choose the optimum translation from search space expressed by weighted directed graph G Tropical semiring + Forward algorithm ->Viterbi semiring
  • 13. k-best • Besides forward-backward algorithm, k-best algorithm is used to optimize route weight • Dijkstra’s algorithm: for single source shortest path problem • Eppstein’s algorithm: for heaping multiple paths efficiently
  • 14. k-best • Assume problem satisfies Tropical semiring and backward algorithm • Calculate and choose max (weight 𝛽(𝑣)) • Fig.5.10 algorithm ・cand: priority queue ・< 𝑣, s>: partial route ・< 𝑣′ ,𝑠′ >: partial route whose vertex 𝑣′ = 𝑣 and edge 𝑠′ = tail 𝑒 = 𝑒 ∈out(𝑣) ・D: set of < 𝑣′ ,𝑠′ >
  • 15. k-best • k=1: Initialized cand • Optimize weight of partial route and whole route Whole route D cand optimal get out < 𝑣, s>,register D Choose 𝑣′ = 𝑣 and 𝑒′ = e ∈out(𝑣) insert to cand heap 𝛽(・) to get optimal k time
  • 16. Limitation of Search Space • If search space is big ->any sort can be forgiven ->calculation amount of decode algorithm become massive ->limitation is necessary: ・Distortion limit, constraint ・Reordering limit, constraint
  • 17. Distortion Constraint • Upper limit setting d for distance between phrase pair ∅ 𝑘and∅ 𝑘−1: start 𝑘 − end 𝑘−1 ≤d The purpose is making model score small if model distorted lead to penalty become big For language pair which do not have big sort, distortion constraint reach good efficiency If d=0: no skip, translate from left to right smoothly ->monotone translation
  • 18. Distortion Constraint • Constraint for case when have partial phrases do not reach the ending point 𝑗: position of the first phrase of source language start 𝑘: the first position of translated phrase If ( 𝑗 < start 𝑘), add end 𝑘 − 𝑗 ≤d ・IBM Constraint 𝑗 𝑠𝑡𝑎𝑟𝑡 𝑘 𝑒𝑛𝑑 𝑘・・・ ∅ 𝑘 phrase No need to exam
  • 19. Beam Search ・Prune disused partial hypothesis and pay attention only partial hypothesis with high score for computational reduction ・Group of vertexs of search graph and prune partial hypothesis which has low score
  • 20. Beam Search ・Group of vertexs of search graph and prune partial hypothesis which has low score Partial hypothesis pruned Partial hypothesis chose
  • 21. Beam Search Some kinds of grouping: - Cover vector grouping - Radix grouping - Beam width pruning - Histogram pruning
  • 22. Heuristic Function • Prevent partial hypothesis which has not been translated yet from pruning • Give predicted score for the rout and learn by A* search so that rout score get the maximum • ->can reduce search error
  • 23. Pre-reordering Method Translation between languages which has significantly different grammatical structure • Pre-reordering rule • Pre-reordering model • Pre-reordering learning
  • 24. Pre-reordering Rule • Based on tree from syntactic analysis, reorder to target language word order • Head-driven phrase structure grammar(HPSG)’s rule: - Syntactic anlysis - Move the subjects back
  • 25. Pre-reordering Model • Source languages must have syntactic analysis tool and morphological analysis tool • Bilingual data are necessary • Probability value of pre-reordering patterns obtained will be estimated by maximum- likelihood estimation(MLE) • Choose the suitable pre-reordering patterns based on reordering part of speech from morphological analysis, or clustering word class
  • 26. Pre-reordering Learning • For language pairs without any syntactic analysis tools and morphological analysis tools • Provisional tree structure automatically generated from syntactic analysis result • Divide tree factors to 2 labels: reordering label [X],and no-reordering label <X> • Use linear ordering problem(LOP) to formulate reordering model to find the approximate solution and build the parse tree

Editor's Notes

  1. 句に基づく機会翻訳のモデルを構築するには、グラフ構造を利用することも考えられます。図5.8,各部分仮説を頂点とし、フレーズ∅が割り当てられる重み付き非周期有向グラフをグラフの各辺のラベルとして表現します。Фはフレーズペアの集合、Aは各辺に割り当てられる重みの集合とします。Vは頂点の集合であり、Eは辺の集合です。
  2. out(v)を頂点vから出ていく辺の集合とし、In(v)を頂点vへ向かう辺の集合とする。このとき、各フレーズペアが表された辺により結ばれる。図5.8では、フレーズペアphrase pair <へ行った, I went to>がで結ばれることが分かりました。
  3. 開始頂点から任意の頂点v∈𝑉へのある経路Ѱは辺の系列Ѱ=( 𝑒 1 , 𝑒 1 ,…, 𝑒 l )として表すことができます。このとき、Ѱの各辺のフレーズペアの原言語側の集合 𝑘=1 𝑙 𝑓 (∅( 𝑒 𝑘 )) ≡ 𝑓 (Ѱ) は、原言語の入力文の部分単語列であり、目的言語側を連結した単語列 𝑒 (∅ 𝑒 1 ),…, 𝑒 (∅ 𝑒 𝑙 ≡ 𝑒 (Ѱ)は、翻訳された目的言語の文の接頭辞に相当する。経路の重みは、各辺の重みの和として表されます。
  4. 「行った、He went」、「へ,to」、「領事館、consulate」という三つのペアで構造される経路により、原言語の単語の集合「」「」「」に対応する目的言語の翻訳文は”He went to the consulate”
  5. 半環は集合に対する加算、乗算という二つの二項演算で定義される。結合性、可換性、分配性という性質を持っている。ただし、加法逆元、および乗法逆元が定義されないのです。
  6. 重み付き有向グラフGにおいて、開始頂点から終了頂点までの経路はѰ= 𝑒 1 , 𝑒 1 ,…, 𝑒 l 。経路のスコアは各部分経路のスコアの積であり、
  7. 半環は分配性を満たすため、図5.7の行11で、加法演算に対応する⊕がGの各頂点について実行されるため、ある頂点vの重みを𝜔(𝑣)とすると
  8. 前向き後ろ向きアルゴリズムをグラフ構造へ一般化したものと考えられます。ここで、topological order(G)はグラフGの頂点を位相的順序に並び替えられたリストとします。𝛼,𝛽:外部変数
  9. 位相的順序の逆順のリスト
  10. 重み付き有向グラフGで表された探索空間から最適な翻訳を選択する問題は、前向きアルゴリズムでTropical半環を用いる経路を記憶することはビタビ半環といいます。
  11. 最適な翻訳を求めるのには、前向きアルゴリズムの他、最短経路問題の解を求めるダイクストラ法、複数の経路をヒープで効率よくするエプシュタイン法があります
  12. Cand:優先度付きキュー、<v,s>部分経路 𝑣 ′ =𝑣 and edge 𝑠 ′ =tail 𝑒 =𝑒∈out(𝑣)だけを列挙
  13. 全体経路から部分経路<v,s>を取り出し、Dへ登録、頂点vの各辺e∈out(𝑣) を列挙して、新しい< 𝑣 ′ , 𝑠 ′ >をキューcandへ挿入する。𝛽(・)が最大になるようねheapでキューcandの各要素の順序を決定する。部分経路のmax𝛽から全体経路の𝛽の最大を求めるアルゴリズムです。
  14. 探索空間が膨大だと、任意の並び変えを許してしまい、デコードのアルゴリズムの計算量が大きくなってしまう。そこで、歪み制限、制約あるいは並べ替え制限、制約などを加え、現実的な計算量を削減する必要がある。
  15. ・原言語の連続するフレーズペア ∅ 𝑘 および ∅ 𝑘−1 の距離に対し上限値dを設定し、歪みモデルによるペナルティが大きい場合には、モデルのスコアが小さくなる。 ・また、原言語の最初の単語をスキップして残りの単語を全てスキップなしで単調に翻訳した場合、最後にスキップされた最初の単語へと戻るために、歪み制約を満たすことができない。そこで、飛びすぎた句があったとしても、戻ることを可能とするように、
  16. ・原言語の連続するフレーズペア ∅ 𝑘 および ∅ 𝑘−1 の距離に対し上限値dを設定し、歪みモデルによるペナルティが大きい場合には、モデルのスコアが小さくなる。 ・また、原言語の最初の単語をスキップして残りの単語を全てスキップなしで単調に翻訳した場合、最後にスキップされた最初の単語へと戻るために、歪み制約を満たすことができない。そこで、飛びすぎた句があったとしても、戻ることを可能とするように、さらに制約を加える。例えば、まだ翻訳されていない、最初の原言語の単語の位置をjとする。つぎにk翻訳されるフレーズペアの最初の位置がjよりも右にあったとき(j<start),最後の位置とjとの距離をd以内とする制約を加える。
  17. ビーム探索では、部分仮説を枝刈りし、高いスコアをもつ部分仮説のみに注目し、近似的に最大化のl問題を解く。ビーム探索では、類似した部分仮説、探索グラフの頂点をグループ化し、各グループごとにスコアの低い部分仮説を枝刈りする。
  18. ビーム探索では、部分仮説を枝刈りし、高いスコアをもつ部分仮説のみに注目し、近似的に最大化のl問題を解く。ビーム探索では、類似した部分仮説、探索グラフの頂点をグループ化し、各グループごとにスコアの低い部分仮説を枝刈りする。
  19. ビーム探索では、部分仮説を枝刈りし、高いスコアをもつ部分仮説のみに注目し、近似的に最大化のl問題を解く。ビーム探索では、類似した部分仮説、探索グラフの頂点をグループ化し、各グループごとにスコアの低い部分仮説を枝刈りする。
  20. 文法構造が大幅n異なる言語間の翻訳を行う時に使う。
  21. HPSGの解析結果から得られる主辞の情報を利用し、主辞を後ろへ移動させると言ったルールー>大幅に機械翻訳の性能を向上させている。
  22. 原言語と目的言語を精通するスペシャリストがいない場合、翻訳が実現不可能。これに対して、両言語の単語アライメントを利用して、並び替えルールを自動的に取得するモデル。 このモデルを使う条件として、原言語に対して構文解析器、あるいは形態素解析器が存在し、かつ対訳データが存在する。各パターンの確率値を最尤推定する。各パターンを適用するモデルを対数線形モデルにより実現し、エントロピー最大法によりそのパラメータを学習する。形態素解析結果から品詞の並び、あるいは、クラスタリングにより単語クラスの並びを用いて並び替えパターンを取得する
  23. 構文解析器から仮の構文解析木が自動的に生成され、を並び替えをしないラベル、並び替えをするラベルに分けられる。並び替えのモデルを線形順序付け問題として定式化し、近似解を見つけ、解析木を構築する