SlideShare une entreprise Scribd logo
1  sur  22
Télécharger pour lire hors ligne
Opinion Mining 
with Deep Recurrent Neural Networks 
EMNLP 2014 reading @ Komachi Lab 
2014/12/04 
All figures and tables in this slide are cited from the paper. 
Komachi Lab. M1 Peinan ZHANG
Introduction 
Fine-grained opinion analysis aims to detect the 
subjective expressions in 
n a text (e.g. “hate” or “like”) 
and to characterize their 
n intensity (e.g. “strong” or “weak”) 
n sentiment (e.g. “negative” or “positive”) 
as well as to identify 
n the opinion holder: the entity expressing the opinion 
n the target, or topic of the opinion: what the opinion is about 
Komachi Lab. M1 Peinan ZHANG 
2
Introduction: Tasks 
Detection of opinion expressions [Wiebe et al., 2005] 
DSEs (Direct Subjective Expressions) 
consist of explicit mentions of private states or speech 
events expressing private states 
ESEs (Expressive Subjective Expressions) 
consist of expressions that indicate sentiment, emotion, etc., 
without explicitly conveying them 
Komachi Lab. M1 Peinan ZHANG 
3
Introduction: Examples 
DSE: explicitly express an opinion holder’s attitude 
ESE: indirectly express the attitude of the writer 
Komachi Lab. M1 Peinan ZHANG 
4
Introduction: Labeling 
Opinion extraction has often been tackled as a sequence 
labeling problem in previous work. 
n B: the beginning of an opinion-related expression 
n I: tokens inside the opinion-related expression 
n O: tokens outside any opinion-related class 
Komachi Lab. M1 Peinan ZHANG 
5
Introduction: Methods (1/3) 
CRFs (Conditional Random Field) 
variants of CRF approaches have been successfully applied to 
opinion expression extraction using this token-based view. 
semiCRF (state-of-the-art) 
relaxes the Markovian assumption inherent to CRFs and operates 
at the phrase level rather then the token level, allowing the 
incorporation of phrase-level features. 
But those CRFs hinges critically on access to an 
appropriate feature set, typically based on 
constituent, dependency parse trees, manually crafted opinion 
lexicons, named entity tagger and other preprocessing 
Komachi Lab. M1 Peinan ZHANG 
6
Introduction: Methods (2/3) 
RNN (Recurrent Neural Network) 
n latent features are modeled as distributed dense vectors of 
hidden layers 
n can operate on sequential data of variable length 
n it can also be applied as a sequence labeler 
bidirectional RNN 
n incorporate information from preceding as well as following 
tokens 
n allowing a lower dimensional dense input representation 
n more compact networks 
Komachi Lab. M1 Peinan ZHANG 
7
Introduction: Methods (3/3) 
Deep Recurrent Network 
n lower levels capture short term interactions among words 
n higher layers reflect interpretations aggregate over longer spans 
n such hierarchies might better model the multi-scale language 
effects 
Deep Bidirectional RNN (the proposed method) 
motivated by the recent success of deep architectures in general 
and deep recurrent networks in particular 
Komachi Lab. M1 Peinan ZHANG 
8
Agenda 
Introduction 
1. Tasks 
2. Examples 
3. Labeling 
4. Methods 
Methodology 
1. Recurrent Neural Network 
2. Bidirectionality 
3. Deep in Space 
Komachi Lab. M1 Peinan ZHANG 
9 
Experiments 
1. Data and Metrics 
2. Baselines 
3. Tuning and Training 
4. Results and Discussion 
Conclusion
Methodology: Recurrent Neural Network 
Elman-type network [Elman, 1990] 
t: step, h0 = 0 
h: hidden layer 
x: input layer 
y: final output layer 
f: nonlinear function (e.g. sigmoid) 
g: output nonlinearity (e.g. softmax) 
Komachi Lab. M1 Peinan ZHANG 
10 
W, V: weight matrices between 
the input and hidden layer 
U: output weight matrix 
b, c: bias vectors
Methodology: Recurrent Neural Network 
Problem with this model: 
the Elman-style unidirectional RNN 
lack the representational power to 
model this task. 
For example: 
n I did not accept his suggestion. 
n I did not go to the rodeo. 
The first example has a DSE phrase “did not accept”. 
However, any such RNN will assign the same labels for the word “did” 
and “not” in both sentences, since the preceding sequences (past) are 
the same. 
Komachi Lab. M1 Peinan ZHANG 
11
Methodology: Bidirectionality 
bidirectional RNN [Schuster et al., 1997] 
→ : forward step (representations of the past) 
← : backward step (representations of the future) 
h0→ = hT+1← = 0 
Note: the forward and backward parts of the network are independent 
of each other until the output layer when they are combined. 
Komachi Lab. M1 Peinan ZHANG 
12
Methodology: Depth in Space (1/2) 
deep RNN: constructed by stacking 
Elman-type RNNs on top of each other 
when i > 1 
Intuitively, every layer of the deep RNN treats the memory sequence of 
the previous layer as the input sequence, and computes its own 
memory representation. 
Komachi Lab. M1 Peinan ZHANG 
13
Methodology: Depth in Space (2/2) 
bidirectional deep RNN 
when i > 1 
To compute the output layer, we only employ the last memory layers. 
Komachi Lab. M1 Peinan ZHANG 
14
Experiments: Data and Metrics 
Data 
MPQA 1.2 corpus [Wiebe et al., 2005] 
n 535 news articles, 11,111 sentences 
n manually annotated w/ both DSEs and ESEs at phrase level 
n 135 development set 
n 10-fold cross validation over remaining 400 documents 
Evaluation Metrics 
Binary Overlap 
count every overlapping match between a predicted and true expression 
as correct 
Proportional Overlap 
impart a partial correctness, proportional to the overlapping amount, to 
each match 
All statistical comparisons are done using a two-sided paired t-test 
with a confidence level of α = .05 
Komachi Lab. M1 Peinan ZHANG 
15
Experiments: Baselines 
Baselines 
n CRF and semiCRF 
n Features: words, POS tag, membership in a manually constructed 
opinion lexicon 
Word Vectors (+VEC) 
n versions of the baselines that have access to pre-trained word 
vectors 
n CRF+VEC: as continuous features per every token 
n semiCRF+VEC: simply take the mean of every word vector for a 
phrase-level vector representation 
n 300-dimensinal 
n trained on part of Google News Dataset (~100B words) 
Komachi Lab. M1 Peinan ZHANG 
16
Experiments: Tuning and Training 
Regularizer 
Dropout: randomly set entries of hidden representations to 0 
with a probability called dropout rate 
Network Training 
n use SGD with fixed learning rate .005 
n update weights after minibatches of 80 sentences 
n run 200 epochs 
n initialized from small random uniform noise 
Komachi Lab. M1 Peinan ZHANG 
17
Experiments: Results and Discussion 
Bidirectional vs. Unidirectional 
Shallow biRNN vs. uniRNN 
n each network has the same number of total parameters 
n 65 hidden units for the unidirectional network 
n 36 hidden units for the bidirectional network 
DSEs 
n Proportional Overlap: 63.83 vs. 60.35 
n Binary Overlap: 69.31 vs. 68.31 
ESEs 
n Proportional Overlap: 54.22 vs. 51.51 
n Binary Overlap: 65.44 vs. 63.65 
Thus, we will not include comparisons to the unidirectional RNNs in 
the remaining experiments. 
Komachi Lab. M1 Peinan ZHANG 
18
Experiments: Results and Discussion 
Komachi Lab. M1 Peinan ZHANG 
19 
Adding Depth 
Bold: Best result 
Asterisk: statistically indis-tinguishable 
performance w/ 
respect to the best 
n for both DSE and ESE, 
3-layer RNN provide 
the best results 
n 2, 3 and 4-layer RNNs 
show equally good 
performance for 
certain sizes 
n adding additional 
layers degrades 
performance
Experiments: Results and Discussion 
Compare with other methods 
Komachi Lab. M1 Peinan ZHANG 
20
Conclusion 
p Explored an application of deep recurrent neural 
networks to the task of sentence-level opinion 
expression. 
p deep RNNs outperformed shallow RNNs. 
p deep RNNs outperformed pervious (semi)CRF 
baselines. 
p One potential future direction is to explore the 
effects of pre-training. 
Komachi Lab. M1 Peinan ZHANG 
21
Agenda 
Introduction 
1. Tasks 
2. Examples 
3. Labeling 
4. Methods 
Methodology 
1. Recurrent Neural Network 
2. Bidirectionality 
3. Deep in Space 
Komachi Lab. M1 Peinan ZHANG 
22 
Experiments 
1. Data and Metrics 
2. Baselines 
3. Tuning and Training 
4. Results and Discussion 
Conclusion

Contenu connexe

Tendances

Master method
Master method Master method
Master method Rajendran
 
Attention in Deep Learning
Attention in Deep LearningAttention in Deep Learning
Attention in Deep Learning健程 杨
 
Operator precedance parsing
Operator precedance parsingOperator precedance parsing
Operator precedance parsingsanchi29
 
Sets and disjoint sets union123
Sets and disjoint sets union123Sets and disjoint sets union123
Sets and disjoint sets union123Ankita Goyal
 
Asymptotic notations
Asymptotic notationsAsymptotic notations
Asymptotic notationsEhtisham Ali
 
Feedforward neural network
Feedforward neural networkFeedforward neural network
Feedforward neural networkSopheaktra YONG
 
K nearest neighbor
K nearest neighborK nearest neighbor
K nearest neighborUjjawal
 
ARTIFICIAL INTELLIGENCE
ARTIFICIAL INTELLIGENCEARTIFICIAL INTELLIGENCE
ARTIFICIAL INTELLIGENCESabique Khan
 
Back tracking and branch and bound class 20
Back tracking and branch and bound class 20Back tracking and branch and bound class 20
Back tracking and branch and bound class 20Kumar
 
Stressen's matrix multiplication
Stressen's matrix multiplicationStressen's matrix multiplication
Stressen's matrix multiplicationKumar
 
5.3 mining sequential patterns
5.3 mining sequential patterns5.3 mining sequential patterns
5.3 mining sequential patternsKrish_ver2
 
Lecture01a correctness
Lecture01a correctnessLecture01a correctness
Lecture01a correctnessSonia Djebali
 
Sum of subsets problem by backtracking 
Sum of subsets problem by backtracking Sum of subsets problem by backtracking 
Sum of subsets problem by backtracking Hasanain Alshadoodee
 
Dynamic programming
Dynamic programmingDynamic programming
Dynamic programmingGopi Saiteja
 
Greedy Algorithm - Knapsack Problem
Greedy Algorithm - Knapsack ProblemGreedy Algorithm - Knapsack Problem
Greedy Algorithm - Knapsack ProblemMadhu Bala
 
Supervised and unsupervised learning
Supervised and unsupervised learningSupervised and unsupervised learning
Supervised and unsupervised learningParas Kohli
 

Tendances (20)

Master method
Master method Master method
Master method
 
Divide and Conquer
Divide and ConquerDivide and Conquer
Divide and Conquer
 
Attention in Deep Learning
Attention in Deep LearningAttention in Deep Learning
Attention in Deep Learning
 
Operator precedance parsing
Operator precedance parsingOperator precedance parsing
Operator precedance parsing
 
Fibonacci Heap
Fibonacci HeapFibonacci Heap
Fibonacci Heap
 
Sets and disjoint sets union123
Sets and disjoint sets union123Sets and disjoint sets union123
Sets and disjoint sets union123
 
Asymptotic notations
Asymptotic notationsAsymptotic notations
Asymptotic notations
 
Feedforward neural network
Feedforward neural networkFeedforward neural network
Feedforward neural network
 
K nearest neighbor
K nearest neighborK nearest neighbor
K nearest neighbor
 
ARTIFICIAL INTELLIGENCE
ARTIFICIAL INTELLIGENCEARTIFICIAL INTELLIGENCE
ARTIFICIAL INTELLIGENCE
 
Back tracking and branch and bound class 20
Back tracking and branch and bound class 20Back tracking and branch and bound class 20
Back tracking and branch and bound class 20
 
Stressen's matrix multiplication
Stressen's matrix multiplicationStressen's matrix multiplication
Stressen's matrix multiplication
 
5.3 mining sequential patterns
5.3 mining sequential patterns5.3 mining sequential patterns
5.3 mining sequential patterns
 
Decision theory
Decision theoryDecision theory
Decision theory
 
Lecture01a correctness
Lecture01a correctnessLecture01a correctness
Lecture01a correctness
 
Sum of subsets problem by backtracking 
Sum of subsets problem by backtracking Sum of subsets problem by backtracking 
Sum of subsets problem by backtracking 
 
Recurrence relation
Recurrence relationRecurrence relation
Recurrence relation
 
Dynamic programming
Dynamic programmingDynamic programming
Dynamic programming
 
Greedy Algorithm - Knapsack Problem
Greedy Algorithm - Knapsack ProblemGreedy Algorithm - Knapsack Problem
Greedy Algorithm - Knapsack Problem
 
Supervised and unsupervised learning
Supervised and unsupervised learningSupervised and unsupervised learning
Supervised and unsupervised learning
 

En vedette

単語分散表現を用いた多層 Denoising Auto-Encoder による評価極性分類
単語分散表現を用いた多層 Denoising Auto-Encoder による評価極性分類単語分散表現を用いた多層 Denoising Auto-Encoder による評価極性分類
単語分散表現を用いた多層 Denoising Auto-Encoder による評価極性分類Peinan ZHANG
 
Recurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRURecurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRUananth
 
20140801ACL2014読み会
20140801ACL2014読み会20140801ACL2014読み会
20140801ACL2014読み会Peinan ZHANG
 
COLING 2014: Joint Opinion Relation Detection Using One-Class Deep Neural Net...
COLING 2014: Joint Opinion Relation Detection Using One-Class Deep Neural Net...COLING 2014: Joint Opinion Relation Detection Using One-Class Deep Neural Net...
COLING 2014: Joint Opinion Relation Detection Using One-Class Deep Neural Net...Peinan ZHANG
 
研究会20140702:進捗報告
研究会20140702:進捗報告研究会20140702:進捗報告
研究会20140702:進捗報告Peinan ZHANG
 
研究会20140618:進捗と闇Pythonistaのワンライナーテクニックを少々
研究会20140618:進捗と闇Pythonistaのワンライナーテクニックを少々研究会20140618:進捗と闇Pythonistaのワンライナーテクニックを少々
研究会20140618:進捗と闇Pythonistaのワンライナーテクニックを少々Peinan ZHANG
 
Introduction to Recurrent Neural Network with Application to Sentiment Analys...
Introduction to Recurrent Neural Network with Application to Sentiment Analys...Introduction to Recurrent Neural Network with Application to Sentiment Analys...
Introduction to Recurrent Neural Network with Application to Sentiment Analys...Artifacia
 
CaseTalk Transformations - 10 slide intro
CaseTalk Transformations - 10 slide introCaseTalk Transformations - 10 slide intro
CaseTalk Transformations - 10 slide introMarco Wobben
 
Workshop The Family - Automate Your Startup
Workshop The Family - Automate Your StartupWorkshop The Family - Automate Your Startup
Workshop The Family - Automate Your StartupGentlenode Studio
 
Timmy Global Health Presentation
Timmy Global Health PresentationTimmy Global Health Presentation
Timmy Global Health PresentationMatt Cummings
 
Waarom schuift paleis andere schaakstukken naar voor?
Waarom schuift paleis andere schaakstukken naar voor?Waarom schuift paleis andere schaakstukken naar voor?
Waarom schuift paleis andere schaakstukken naar voor?Thierry Debels
 
Web browsers & the realtime web
Web browsers & the realtime webWeb browsers & the realtime web
Web browsers & the realtime webPhil Leggetter
 
My inspirational person english
My inspirational person englishMy inspirational person english
My inspirational person englishPao Tati
 
Revision SD 4 SEMESTER GENAP T.P. 2015-2016 UNIT 16
Revision SD 4 SEMESTER GENAP T.P. 2015-2016 UNIT 16Revision SD 4 SEMESTER GENAP T.P. 2015-2016 UNIT 16
Revision SD 4 SEMESTER GENAP T.P. 2015-2016 UNIT 16Agnes Yodo
 
Bilingue si cresce - un incontro sul bilinguismo infantile
Bilingue si cresce - un incontro sul bilinguismo infantileBilingue si cresce - un incontro sul bilinguismo infantile
Bilingue si cresce - un incontro sul bilinguismo infantileEsedra Srl
 
Next Generation Leadership: Integrated Talent Management for Robust Talent Pi...
Next Generation Leadership: Integrated Talent Management for Robust Talent Pi...Next Generation Leadership: Integrated Talent Management for Robust Talent Pi...
Next Generation Leadership: Integrated Talent Management for Robust Talent Pi...National HRD Network
 

En vedette (20)

単語分散表現を用いた多層 Denoising Auto-Encoder による評価極性分類
単語分散表現を用いた多層 Denoising Auto-Encoder による評価極性分類単語分散表現を用いた多層 Denoising Auto-Encoder による評価極性分類
単語分散表現を用いた多層 Denoising Auto-Encoder による評価極性分類
 
Recurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRURecurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRU
 
20140801ACL2014読み会
20140801ACL2014読み会20140801ACL2014読み会
20140801ACL2014読み会
 
COLING 2014: Joint Opinion Relation Detection Using One-Class Deep Neural Net...
COLING 2014: Joint Opinion Relation Detection Using One-Class Deep Neural Net...COLING 2014: Joint Opinion Relation Detection Using One-Class Deep Neural Net...
COLING 2014: Joint Opinion Relation Detection Using One-Class Deep Neural Net...
 
研究会20140702:進捗報告
研究会20140702:進捗報告研究会20140702:進捗報告
研究会20140702:進捗報告
 
研究会20140618:進捗と闇Pythonistaのワンライナーテクニックを少々
研究会20140618:進捗と闇Pythonistaのワンライナーテクニックを少々研究会20140618:進捗と闇Pythonistaのワンライナーテクニックを少々
研究会20140618:進捗と闇Pythonistaのワンライナーテクニックを少々
 
Introduction to Recurrent Neural Network with Application to Sentiment Analys...
Introduction to Recurrent Neural Network with Application to Sentiment Analys...Introduction to Recurrent Neural Network with Application to Sentiment Analys...
Introduction to Recurrent Neural Network with Application to Sentiment Analys...
 
CaseTalk Transformations - 10 slide intro
CaseTalk Transformations - 10 slide introCaseTalk Transformations - 10 slide intro
CaseTalk Transformations - 10 slide intro
 
Workshop The Family - Automate Your Startup
Workshop The Family - Automate Your StartupWorkshop The Family - Automate Your Startup
Workshop The Family - Automate Your Startup
 
Timmy Global Health Presentation
Timmy Global Health PresentationTimmy Global Health Presentation
Timmy Global Health Presentation
 
Waarom schuift paleis andere schaakstukken naar voor?
Waarom schuift paleis andere schaakstukken naar voor?Waarom schuift paleis andere schaakstukken naar voor?
Waarom schuift paleis andere schaakstukken naar voor?
 
Web Tricks
Web TricksWeb Tricks
Web Tricks
 
kyle
kylekyle
kyle
 
Vplyv online kampaní na offline výsledky
Vplyv online kampaní na offline výsledkyVplyv online kampaní na offline výsledky
Vplyv online kampaní na offline výsledky
 
Web browsers & the realtime web
Web browsers & the realtime webWeb browsers & the realtime web
Web browsers & the realtime web
 
My inspirational person english
My inspirational person englishMy inspirational person english
My inspirational person english
 
Revision SD 4 SEMESTER GENAP T.P. 2015-2016 UNIT 16
Revision SD 4 SEMESTER GENAP T.P. 2015-2016 UNIT 16Revision SD 4 SEMESTER GENAP T.P. 2015-2016 UNIT 16
Revision SD 4 SEMESTER GENAP T.P. 2015-2016 UNIT 16
 
Bilingue si cresce - un incontro sul bilinguismo infantile
Bilingue si cresce - un incontro sul bilinguismo infantileBilingue si cresce - un incontro sul bilinguismo infantile
Bilingue si cresce - un incontro sul bilinguismo infantile
 
Next Generation Leadership: Integrated Talent Management for Robust Talent Pi...
Next Generation Leadership: Integrated Talent Management for Robust Talent Pi...Next Generation Leadership: Integrated Talent Management for Robust Talent Pi...
Next Generation Leadership: Integrated Talent Management for Robust Talent Pi...
 
El petroleo
El petroleoEl petroleo
El petroleo
 

Similaire à EMNLP 2014: Opinion Mining with Deep Recurrent Neural Network

Colloquium talk on modal sense classification using a convolutional neural ne...
Colloquium talk on modal sense classification using a convolutional neural ne...Colloquium talk on modal sense classification using a convolutional neural ne...
Colloquium talk on modal sense classification using a convolutional neural ne...Ana Marasović
 
Adaptive Training of Radial Basis Function Networks Based on Cooperative
Adaptive Training of Radial Basis Function Networks Based on CooperativeAdaptive Training of Radial Basis Function Networks Based on Cooperative
Adaptive Training of Radial Basis Function Networks Based on CooperativeESCOM
 
Turkish language modeling using BERT
Turkish language modeling using BERTTurkish language modeling using BERT
Turkish language modeling using BERTAbdurrahimDerric
 
Fast and Accurate Preordering for SMT using Neural Networks
Fast and Accurate Preordering for SMT using Neural NetworksFast and Accurate Preordering for SMT using Neural Networks
Fast and Accurate Preordering for SMT using Neural NetworksSDL
 
deepnet-lourentzou.ppt
deepnet-lourentzou.pptdeepnet-lourentzou.ppt
deepnet-lourentzou.pptyang947066
 
ANN Based POS Tagging For Nepali Text
ANN Based POS Tagging For Nepali Text ANN Based POS Tagging For Nepali Text
ANN Based POS Tagging For Nepali Text ijnlc
 
NEURALNETWORKS_DM_SOWMYAJYOTHI.pdf
NEURALNETWORKS_DM_SOWMYAJYOTHI.pdfNEURALNETWORKS_DM_SOWMYAJYOTHI.pdf
NEURALNETWORKS_DM_SOWMYAJYOTHI.pdfSowmyaJyothi3
 
Deep Neural Methods for Retrieval
Deep Neural Methods for RetrievalDeep Neural Methods for Retrieval
Deep Neural Methods for RetrievalBhaskar Mitra
 
Attention Is All You Need
Attention Is All You NeedAttention Is All You Need
Attention Is All You NeedSEMINARGROOT
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learningJunaid Bhat
 
20141003.journal club
20141003.journal club20141003.journal club
20141003.journal clubHayaru SHOUNO
 
Sentence Validation by Statistical Language Modeling and Semantic Relations
Sentence Validation by Statistical Language Modeling and Semantic RelationsSentence Validation by Statistical Language Modeling and Semantic Relations
Sentence Validation by Statistical Language Modeling and Semantic RelationsEditor IJCATR
 
A New Classifier Based onRecurrent Neural Network Using Multiple Binary-Outpu...
A New Classifier Based onRecurrent Neural Network Using Multiple Binary-Outpu...A New Classifier Based onRecurrent Neural Network Using Multiple Binary-Outpu...
A New Classifier Based onRecurrent Neural Network Using Multiple Binary-Outpu...iosrjce
 

Similaire à EMNLP 2014: Opinion Mining with Deep Recurrent Neural Network (20)

Icon18revrec sudeshna
Icon18revrec sudeshnaIcon18revrec sudeshna
Icon18revrec sudeshna
 
CNN for modeling sentence
CNN for modeling sentenceCNN for modeling sentence
CNN for modeling sentence
 
2224d_final
2224d_final2224d_final
2224d_final
 
Colloquium talk on modal sense classification using a convolutional neural ne...
Colloquium talk on modal sense classification using a convolutional neural ne...Colloquium talk on modal sense classification using a convolutional neural ne...
Colloquium talk on modal sense classification using a convolutional neural ne...
 
Adaptive Training of Radial Basis Function Networks Based on Cooperative
Adaptive Training of Radial Basis Function Networks Based on CooperativeAdaptive Training of Radial Basis Function Networks Based on Cooperative
Adaptive Training of Radial Basis Function Networks Based on Cooperative
 
Turkish language modeling using BERT
Turkish language modeling using BERTTurkish language modeling using BERT
Turkish language modeling using BERT
 
Generative models
Generative modelsGenerative models
Generative models
 
Fast and Accurate Preordering for SMT using Neural Networks
Fast and Accurate Preordering for SMT using Neural NetworksFast and Accurate Preordering for SMT using Neural Networks
Fast and Accurate Preordering for SMT using Neural Networks
 
DL for molecules
DL for moleculesDL for molecules
DL for molecules
 
deepnet-lourentzou.ppt
deepnet-lourentzou.pptdeepnet-lourentzou.ppt
deepnet-lourentzou.ppt
 
ANN Based POS Tagging For Nepali Text
ANN Based POS Tagging For Nepali Text ANN Based POS Tagging For Nepali Text
ANN Based POS Tagging For Nepali Text
 
NEURALNETWORKS_DM_SOWMYAJYOTHI.pdf
NEURALNETWORKS_DM_SOWMYAJYOTHI.pdfNEURALNETWORKS_DM_SOWMYAJYOTHI.pdf
NEURALNETWORKS_DM_SOWMYAJYOTHI.pdf
 
Deep Neural Methods for Retrieval
Deep Neural Methods for RetrievalDeep Neural Methods for Retrieval
Deep Neural Methods for Retrieval
 
Attention Is All You Need
Attention Is All You NeedAttention Is All You Need
Attention Is All You Need
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
20141003.journal club
20141003.journal club20141003.journal club
20141003.journal club
 
Sentence Validation by Statistical Language Modeling and Semantic Relations
Sentence Validation by Statistical Language Modeling and Semantic RelationsSentence Validation by Statistical Language Modeling and Semantic Relations
Sentence Validation by Statistical Language Modeling and Semantic Relations
 
Seminar
SeminarSeminar
Seminar
 
H017376369
H017376369H017376369
H017376369
 
A New Classifier Based onRecurrent Neural Network Using Multiple Binary-Outpu...
A New Classifier Based onRecurrent Neural Network Using Multiple Binary-Outpu...A New Classifier Based onRecurrent Neural Network Using Multiple Binary-Outpu...
A New Classifier Based onRecurrent Neural Network Using Multiple Binary-Outpu...
 

Dernier

Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessPixlogix Infotech
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?Antenna Manufacturer Coco
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxMalak Abu Hammad
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 

Dernier (20)

Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your Business
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 

EMNLP 2014: Opinion Mining with Deep Recurrent Neural Network

  • 1. Opinion Mining with Deep Recurrent Neural Networks EMNLP 2014 reading @ Komachi Lab 2014/12/04 All figures and tables in this slide are cited from the paper. Komachi Lab. M1 Peinan ZHANG
  • 2. Introduction Fine-grained opinion analysis aims to detect the subjective expressions in n a text (e.g. “hate” or “like”) and to characterize their n intensity (e.g. “strong” or “weak”) n sentiment (e.g. “negative” or “positive”) as well as to identify n the opinion holder: the entity expressing the opinion n the target, or topic of the opinion: what the opinion is about Komachi Lab. M1 Peinan ZHANG 2
  • 3. Introduction: Tasks Detection of opinion expressions [Wiebe et al., 2005] DSEs (Direct Subjective Expressions) consist of explicit mentions of private states or speech events expressing private states ESEs (Expressive Subjective Expressions) consist of expressions that indicate sentiment, emotion, etc., without explicitly conveying them Komachi Lab. M1 Peinan ZHANG 3
  • 4. Introduction: Examples DSE: explicitly express an opinion holder’s attitude ESE: indirectly express the attitude of the writer Komachi Lab. M1 Peinan ZHANG 4
  • 5. Introduction: Labeling Opinion extraction has often been tackled as a sequence labeling problem in previous work. n B: the beginning of an opinion-related expression n I: tokens inside the opinion-related expression n O: tokens outside any opinion-related class Komachi Lab. M1 Peinan ZHANG 5
  • 6. Introduction: Methods (1/3) CRFs (Conditional Random Field) variants of CRF approaches have been successfully applied to opinion expression extraction using this token-based view. semiCRF (state-of-the-art) relaxes the Markovian assumption inherent to CRFs and operates at the phrase level rather then the token level, allowing the incorporation of phrase-level features. But those CRFs hinges critically on access to an appropriate feature set, typically based on constituent, dependency parse trees, manually crafted opinion lexicons, named entity tagger and other preprocessing Komachi Lab. M1 Peinan ZHANG 6
  • 7. Introduction: Methods (2/3) RNN (Recurrent Neural Network) n latent features are modeled as distributed dense vectors of hidden layers n can operate on sequential data of variable length n it can also be applied as a sequence labeler bidirectional RNN n incorporate information from preceding as well as following tokens n allowing a lower dimensional dense input representation n more compact networks Komachi Lab. M1 Peinan ZHANG 7
  • 8. Introduction: Methods (3/3) Deep Recurrent Network n lower levels capture short term interactions among words n higher layers reflect interpretations aggregate over longer spans n such hierarchies might better model the multi-scale language effects Deep Bidirectional RNN (the proposed method) motivated by the recent success of deep architectures in general and deep recurrent networks in particular Komachi Lab. M1 Peinan ZHANG 8
  • 9. Agenda Introduction 1. Tasks 2. Examples 3. Labeling 4. Methods Methodology 1. Recurrent Neural Network 2. Bidirectionality 3. Deep in Space Komachi Lab. M1 Peinan ZHANG 9 Experiments 1. Data and Metrics 2. Baselines 3. Tuning and Training 4. Results and Discussion Conclusion
  • 10. Methodology: Recurrent Neural Network Elman-type network [Elman, 1990] t: step, h0 = 0 h: hidden layer x: input layer y: final output layer f: nonlinear function (e.g. sigmoid) g: output nonlinearity (e.g. softmax) Komachi Lab. M1 Peinan ZHANG 10 W, V: weight matrices between the input and hidden layer U: output weight matrix b, c: bias vectors
  • 11. Methodology: Recurrent Neural Network Problem with this model: the Elman-style unidirectional RNN lack the representational power to model this task. For example: n I did not accept his suggestion. n I did not go to the rodeo. The first example has a DSE phrase “did not accept”. However, any such RNN will assign the same labels for the word “did” and “not” in both sentences, since the preceding sequences (past) are the same. Komachi Lab. M1 Peinan ZHANG 11
  • 12. Methodology: Bidirectionality bidirectional RNN [Schuster et al., 1997] → : forward step (representations of the past) ← : backward step (representations of the future) h0→ = hT+1← = 0 Note: the forward and backward parts of the network are independent of each other until the output layer when they are combined. Komachi Lab. M1 Peinan ZHANG 12
  • 13. Methodology: Depth in Space (1/2) deep RNN: constructed by stacking Elman-type RNNs on top of each other when i > 1 Intuitively, every layer of the deep RNN treats the memory sequence of the previous layer as the input sequence, and computes its own memory representation. Komachi Lab. M1 Peinan ZHANG 13
  • 14. Methodology: Depth in Space (2/2) bidirectional deep RNN when i > 1 To compute the output layer, we only employ the last memory layers. Komachi Lab. M1 Peinan ZHANG 14
  • 15. Experiments: Data and Metrics Data MPQA 1.2 corpus [Wiebe et al., 2005] n 535 news articles, 11,111 sentences n manually annotated w/ both DSEs and ESEs at phrase level n 135 development set n 10-fold cross validation over remaining 400 documents Evaluation Metrics Binary Overlap count every overlapping match between a predicted and true expression as correct Proportional Overlap impart a partial correctness, proportional to the overlapping amount, to each match All statistical comparisons are done using a two-sided paired t-test with a confidence level of α = .05 Komachi Lab. M1 Peinan ZHANG 15
  • 16. Experiments: Baselines Baselines n CRF and semiCRF n Features: words, POS tag, membership in a manually constructed opinion lexicon Word Vectors (+VEC) n versions of the baselines that have access to pre-trained word vectors n CRF+VEC: as continuous features per every token n semiCRF+VEC: simply take the mean of every word vector for a phrase-level vector representation n 300-dimensinal n trained on part of Google News Dataset (~100B words) Komachi Lab. M1 Peinan ZHANG 16
  • 17. Experiments: Tuning and Training Regularizer Dropout: randomly set entries of hidden representations to 0 with a probability called dropout rate Network Training n use SGD with fixed learning rate .005 n update weights after minibatches of 80 sentences n run 200 epochs n initialized from small random uniform noise Komachi Lab. M1 Peinan ZHANG 17
  • 18. Experiments: Results and Discussion Bidirectional vs. Unidirectional Shallow biRNN vs. uniRNN n each network has the same number of total parameters n 65 hidden units for the unidirectional network n 36 hidden units for the bidirectional network DSEs n Proportional Overlap: 63.83 vs. 60.35 n Binary Overlap: 69.31 vs. 68.31 ESEs n Proportional Overlap: 54.22 vs. 51.51 n Binary Overlap: 65.44 vs. 63.65 Thus, we will not include comparisons to the unidirectional RNNs in the remaining experiments. Komachi Lab. M1 Peinan ZHANG 18
  • 19. Experiments: Results and Discussion Komachi Lab. M1 Peinan ZHANG 19 Adding Depth Bold: Best result Asterisk: statistically indis-tinguishable performance w/ respect to the best n for both DSE and ESE, 3-layer RNN provide the best results n 2, 3 and 4-layer RNNs show equally good performance for certain sizes n adding additional layers degrades performance
  • 20. Experiments: Results and Discussion Compare with other methods Komachi Lab. M1 Peinan ZHANG 20
  • 21. Conclusion p Explored an application of deep recurrent neural networks to the task of sentence-level opinion expression. p deep RNNs outperformed shallow RNNs. p deep RNNs outperformed pervious (semi)CRF baselines. p One potential future direction is to explore the effects of pre-training. Komachi Lab. M1 Peinan ZHANG 21
  • 22. Agenda Introduction 1. Tasks 2. Examples 3. Labeling 4. Methods Methodology 1. Recurrent Neural Network 2. Bidirectionality 3. Deep in Space Komachi Lab. M1 Peinan ZHANG 22 Experiments 1. Data and Metrics 2. Baselines 3. Tuning and Training 4. Results and Discussion Conclusion