Adaptive Multi-Compositionality for Recursive Neural Models with Applications to Sentiment Analysis. July 31, 2014
|
|
- Phillip Phillips
- 5 years ago
- Views:
Transcription
1 Adaptive Multi-Compositionality for Recursive Neural Models with Applications to Sentiment Analysis July 31, 2014
2 Semantic Composition Principle of Compositionality The meaning of a complex expression is determined by the meanings of its constituent expressions and the rules used to combine them Compositional nature of natural language Go beyond words towards sentences Examples red car -> red + car not very good -> not + ( very + good ) eat food -> eat + food
3 Recursive Neural Models (RNMs) Utilize the recursive structures of sentences to obtain the semantic representations The vector representations are used as features and fed into a softmax classifier to predict their labels Learn to recursively perform semantic compositions in vector space One family of the popular deep learning models Negative not very good Softmax very good not very good
4 Semantic Composition with Matrix/Tensor The main difference among the recursive neural models (RNMs) lies in semantic composition methods v v l v r intersection v = f v = f v = f W v l v r + b v = f RNN (Socher et al. 2011) RNTN (Yu et al. 2013, Socher et al. 2013) Problem: RNN and RNTN employ the same global composition function for all pair of input vectors v l v r T T [1:D] v l v r + W v l v r + b
5 Motivation of This Work Use different composition functions for different types of compositions Negation: not good, not bad Intensification: very good, pretty bad Contrast: the movie is good, but I love it Sentiment word + target/aspect: good movie, low price Model the composition as a distribution over multiple composition functions, and adaptively select them
6 One Global Composition Function Adaptive Multi-Compositionality
7 Adaptive Compositionality Use more than one composition functions and adaptively select them depending on the input vectors v = f C h=1 P g h v l, v r g h v l, v r Output vector Distribution of composition functions g 1 g 2 g 3 g 4 Classifier Softmax Input vectors
8 Adaptive Compositionality Use more than one composition functions and adaptively select them depending on the input vectors C Output vector v = f P g h v l, v r g h v l, v r h=1 The h -th composition function (Both the matrices and tensors can be used) Distribution of composition functions g 1 g 2 g 3 g 4 Classifier Softmax Input vectors
9 Adaptive Compositionality Use more than one composition functions and adaptively select them depending on the input vectors v = f C h=1 P g h v l, v r g h v l, v r Output vector Distribution of composition functions P g 1 v l, v r P g C v l, v r = softmax βs v l v r The Boltzmann distribution is used to adaptively select g h. g 1 g 2 g 3 g 4 Classifier Softmax Input vectors P g h v l, v r = 1 C P g 1 v l, v r P g C v l, v r = softmax S v l v r P g h v l, v r = 1, maxmum score 0, otherwise Avg-AdaMC Weighted-AdaMC Max-AdaMC
10 Objective Function Minimize the cross-entropy error Target vector t j = [0 1 0] Predicted distribution y j = [ ] min Θ E Θ = AdaGrad (Duchi, Hazan, and Singer 2011) i j t j i log y j i + θ Θ λ θ θ 2 2 θ t = θ t 1 η G t = G t G t E E θ θ=θt 1 θ θ=θt 1 2
11 Parameter Estimation Back-propagation algorithm: Classification: E U mn = i [v n i (y m i t m i )] δ m i r = k k y m i t m i U mk f (a m i ), r = i par(i) par(i) r a δ k m f (a i m ), r anc(i) v m i Composition selection: E S mn = i r bp(i) k i r δ k h i r δ k a k i,g h x n i βp g h v l i, v r i P g h v l i, v r i 1, h = m a k i,g h x n i βp g h v l i, v r i P g m v l i, v r i, h m i r bp(i) k h Linear composition: Tensor Composition: E W mn = i r bp(i) δ m i r x n i P g h v l i, v r i E V h [d] mn = i r bp(i) δ d i r x m i x n i P g h v l i, v r i Word Embedding: E L d w = i =w r bp(i) δ d i r
12 Stanford Sentiment Treebank 10,662 critic reviews in Rotten Tomatoes 215,154 phrases from results of Stanford Parser The workers in Amazon Mechanical Turk annotate polarity levels for all these phrases The sentiment scales are merged to five categories (very negative, negative, neutral, positive, very positive)
13 Results of evaluation on the Sentiment Treebank. The top three methods are in bold. Our methods achieve best performances when \beta is set to 2.
14 v = f C h=1 P g h v l, v r g h v l, v r P g h v l, v r = 1 C P g 1 v l, v r P g C v l, v r = softmax S v l v r P g h v l, v r = 1, max score 0, otherwise P g 1 v l, v r P g C v l, v r = softmax βs v l v r Avg-AdaMC Weighted-AdaMC Max-AdaMC
15 Vector Representations Word/Phrase good boring ingenious soundtrack good actors thought-provoking film painfully bad not a good movie Neighboring Words/Phrases in the Vector Space cool, fantasy, classic, watchable, attractive dull, bad, disappointing, horrible, annoying extraordinary, inspirational, imaginative, thoughtful, creative execution, animation, cast, colors, scene good ideas, good acting, good looks, good sense, great cast beautiful film, engaging film, lovely film, remarkable film, riveting story how bad, too bad, really bad, so bad, very bad isn t much fun, isn t very funny, nothing new, isn t as funny of clichés
16 fancy, good, cool, promising, interested Positive Objective plot, near, buy, surface, them, version Very negative failure, worst, disaster, horrible problem, slow, sick, mess, poor, wrong Negative Very positive creative, great, perfect, superb, amazing t-sne
17 Composition Pairs in the Composition Space For the composition pair (v l, v r ), we use the distribution of the composition functions P g 1 v l, v r P g C v l, v r to query its neighboring pairs Composition Pair really bad (is n t) (necessarily bad) great (Broadway play) Neighboring Composition Pairs very bad / only dull / much bad / extremely bad / (all that) bad (is n t) (painfully bad) / not mean-spirited / not (too slow) / not well-acted / (have otherwise) (been bland) great (cinematic innovation) / great subject / great performance / energetic entertainment / great (comedy filmmaker) (arty and) jazzy (Smart and) fun / (verve and) fun / (unique and) entertaining / (gentle and) engrossing / (warmth and) humor
18 these/this/the * Visualization: Composition Pairs P g 1 v l, v r P g C v l, v r * and for/with * and * adj noun (*) Entity Negation Intensification verb * * s a/an/two * of * t-sne
19 these/this/the * * and for/with * and * adj noun (*) NE Negation Intensification verb * * s a/an/two * Best films Riveting story Solid cast Talented director Gorgeous visuals of *
20 these/this/the * * and for/with * and * adj noun (*) Entity Negation Intensification verb * * s a/an/two * Really good Quite funny Damn fine Very good Particularly funny of *
21 these/this/the * * and for/with * and * adj noun (*) Entity Negation Intensification verb * * s a/an/two * Is never dull Not smart Not a good movie Is n t much fun Wo n t be disappointed of *
22 these/this/the * * and for/with * and * adj noun (*) Entity Negation Intensification verb * * s a/an/two * Roberto Alagna Pearl Harbor Elizabeth Hurley Diane Lane Pauly Shore of *
23 Future Work Use AdaMC for the other NLP tasks Utilize external information to adaptively select the composition functions Part-of-speech tags Syntactic parsing results Mix different composition types together Linear combination approach (RNN) Tensor-based approach (RNTN) Multiplication approach
24 THANKS!
Deep Learning For Mathematical Functions
000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050
More informationOnline Videos FERPA. Sign waiver or sit on the sides or in the back. Off camera question time before and after lecture. Questions?
Online Videos FERPA Sign waiver or sit on the sides or in the back Off camera question time before and after lecture Questions? Lecture 1, Slide 1 CS224d Deep NLP Lecture 4: Word Window Classification
More informationUncertainty in prediction. Can we usually expect to get a perfect classifier, if we have enough training data?
Logistic regression Uncertainty in prediction Can we usually expect to get a perfect classifier, if we have enough training data? Uncertainty in prediction Can we usually expect to get a perfect classifier,
More informationLogistic regression for conditional probability estimation
Logistic regression for conditional probability estimation Instructor: Taylor Berg-Kirkpatrick Slides: Sanjoy Dasgupta Course website: http://cseweb.ucsd.edu/classes/wi19/cse151-b/ Uncertainty in prediction
More information10/17/04. Today s Main Points
Part-of-speech Tagging & Hidden Markov Model Intro Lecture #10 Introduction to Natural Language Processing CMPSCI 585, Fall 2004 University of Massachusetts Amherst Andrew McCallum Today s Main Points
More informationProbabilistic Graphical Models: MRFs and CRFs. CSE628: Natural Language Processing Guest Lecturer: Veselin Stoyanov
Probabilistic Graphical Models: MRFs and CRFs CSE628: Natural Language Processing Guest Lecturer: Veselin Stoyanov Why PGMs? PGMs can model joint probabilities of many events. many techniques commonly
More informationExtraction of Opposite Sentiments in Classified Free Format Text Reviews
Extraction of Opposite Sentiments in Classified Free Format Text Reviews Dong (Haoyuan) Li 1, Anne Laurent 2, Mathieu Roche 2, and Pascal Poncelet 1 1 LGI2P - École des Mines d Alès, Parc Scientifique
More informationSpatial Role Labeling CS365 Course Project
Spatial Role Labeling CS365 Course Project Amit Kumar, akkumar@iitk.ac.in Chandra Sekhar, gchandra@iitk.ac.in Supervisor : Dr.Amitabha Mukerjee ABSTRACT In natural language processing one of the important
More informationAPPLIED DEEP LEARNING PROF ALEXIEI DINGLI
APPLIED DEEP LEARNING PROF ALEXIEI DINGLI TECH NEWS TECH NEWS HOW TO DO IT? TECH NEWS APPLICATIONS TECH NEWS TECH NEWS NEURAL NETWORKS Interconnected set of nodes and edges Designed to perform complex
More informationDeep Learning for Natural Language Processing. Sidharth Mudgal April 4, 2017
Deep Learning for Natural Language Processing Sidharth Mudgal April 4, 2017 Table of contents 1. Intro 2. Word Vectors 3. Word2Vec 4. Char Level Word Embeddings 5. Application: Entity Matching 6. Conclusion
More informationA Survey of Techniques for Sentiment Analysis in Movie Reviews and Deep Stochastic Recurrent Nets
A Survey of Techniques for Sentiment Analysis in Movie Reviews and Deep Stochastic Recurrent Nets Chase Lochmiller Department of Computer Science Stanford University cjloch11@stanford.edu Abstract In this
More informationLecture 13: Structured Prediction
Lecture 13: Structured Prediction Kai-Wei Chang CS @ University of Virginia kw@kwchang.net Couse webpage: http://kwchang.net/teaching/nlp16 CS6501: NLP 1 Quiz 2 v Lectures 9-13 v Lecture 12: before page
More informationNatural Language Processing with Deep Learning CS224N/Ling284
Natural Language Processing with Deep Learning CS224N/Ling284 Lecture 4: Word Window Classification and Neural Networks Richard Socher Organization Main midterm: Feb 13 Alternative midterm: Friday Feb
More informationMulti-theme Sentiment Analysis using Quantified Contextual
Multi-theme Sentiment Analysis using Quantified Contextual Valence Shifters Hongkun Yu, Jingbo Shang, MeichunHsu, Malú Castellanos, Jiawei Han Presented by Jingbo Shang University of Illinois at Urbana-Champaign
More informationParsing with Context-Free Grammars
Parsing with Context-Free Grammars Berlin Chen 2005 References: 1. Natural Language Understanding, chapter 3 (3.1~3.4, 3.6) 2. Speech and Language Processing, chapters 9, 10 NLP-Berlin Chen 1 Grammars
More informationSemi-Supervised Recursive Autoencoder
Semi-Supervised Recursive Autoencoder Si Chen and Yufei Wang Department of Electrical and Computer Engineering University of California San Diego {sic046, yuw176}@ucsd.edu Abstract In this project, we
More informationSpatial Transformer. Ref: Max Jaderberg, Karen Simonyan, Andrew Zisserman, Koray Kavukcuoglu, Spatial Transformer Networks, NIPS, 2015
Spatial Transormer Re: Max Jaderberg, Karen Simonyan, Andrew Zisserman, Koray Kavukcuoglu, Spatial Transormer Networks, NIPS, 2015 Spatial Transormer Layer CNN is not invariant to scaling and rotation
More informationPOS-Tagging. Fabian M. Suchanek
POS-Tagging Fabian M. Suchanek 100 Def: POS A Part-of-Speech (also: POS, POS-tag, word class, lexical class, lexical category) is a set of words with the same grammatical role. Alizée wrote a really great
More informationNeural Networks for NLP. COMP-599 Nov 30, 2016
Neural Networks for NLP COMP-599 Nov 30, 2016 Outline Neural networks and deep learning: introduction Feedforward neural networks word2vec Complex neural network architectures Convolutional neural networks
More informationLecture 2: Probability, Naive Bayes
Lecture 2: Probability, Naive Bayes CS 585, Fall 205 Introduction to Natural Language Processing http://people.cs.umass.edu/~brenocon/inlp205/ Brendan O Connor Today Probability Review Naive Bayes classification
More informationSequence Modeling with Neural Networks
Sequence Modeling with Neural Networks Harini Suresh y 0 y 1 y 2 s 0 s 1 s 2... x 0 x 1 x 2 hat is a sequence? This morning I took the dog for a walk. sentence medical signals speech waveform Successes
More informationDISTRIBUTIONAL SEMANTICS
COMP90042 LECTURE 4 DISTRIBUTIONAL SEMANTICS LEXICAL DATABASES - PROBLEMS Manually constructed Expensive Human annotation can be biased and noisy Language is dynamic New words: slangs, terminology, etc.
More informationDepartment of Computer Science and Engineering Indian Institute of Technology, Kanpur. Spatial Role Labeling
Department of Computer Science and Engineering Indian Institute of Technology, Kanpur CS 365 Artificial Intelligence Project Report Spatial Role Labeling Submitted by Satvik Gupta (12633) and Garvit Pahal
More informationRegularization Introduction to Machine Learning. Matt Gormley Lecture 10 Feb. 19, 2018
1-61 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Regularization Matt Gormley Lecture 1 Feb. 19, 218 1 Reminders Homework 4: Logistic
More informationMore on HMMs and other sequence models. Intro to NLP - ETHZ - 18/03/2013
More on HMMs and other sequence models Intro to NLP - ETHZ - 18/03/2013 Summary Parts of speech tagging HMMs: Unsupervised parameter estimation Forward Backward algorithm Bayesian variants Discriminative
More informationMachine Learning Basics
Security and Fairness of Deep Learning Machine Learning Basics Anupam Datta CMU Spring 2019 Image Classification Image Classification Image classification pipeline Input: A training set of N images, each
More informationBag of Words Meets Bags of Popcorn
Sentiment Analysis via and Natural Language Processing Tarleton State University July 16, 2015 Data Description Sentiment Score tf-idf NDSI AFINN List word score invincible 2 mirthful 3 flops -2 hypocritical
More informationCS224N: Natural Language Processing with Deep Learning Winter 2017 Midterm Exam
CS224N: Natural Language Processing with Deep Learning Winter 2017 Midterm Exam This examination consists of 14 printed sides, 5 questions, and 100 points. The exam accounts for 17% of your total grade.
More informationSemantics with Dense Vectors. Reference: D. Jurafsky and J. Martin, Speech and Language Processing
Semantics with Dense Vectors Reference: D. Jurafsky and J. Martin, Speech and Language Processing 1 Semantics with Dense Vectors We saw how to represent a word as a sparse vector with dimensions corresponding
More informationTask-Oriented Dialogue System (Young, 2000)
2 Review Task-Oriented Dialogue System (Young, 2000) 3 http://rsta.royalsocietypublishing.org/content/358/1769/1389.short Speech Signal Speech Recognition Hypothesis are there any action movies to see
More informationLecture 11 Recurrent Neural Networks I
Lecture 11 Recurrent Neural Networks I CMSC 35246: Deep Learning Shubhendu Trivedi & Risi Kondor University of Chicago May 01, 2017 Introduction Sequence Learning with Neural Networks Some Sequence Tasks
More informationApplied Natural Language Processing
Applied Natural Language Processing Info 256 Lecture 20: Sequence labeling (April 9, 2019) David Bamman, UC Berkeley POS tagging NNP Labeling the tag that s correct for the context. IN JJ FW SYM IN JJ
More informationCS224N: Natural Language Processing with Deep Learning Winter 2018 Midterm Exam
CS224N: Natural Language Processing with Deep Learning Winter 2018 Midterm Exam This examination consists of 17 printed sides, 5 questions, and 100 points. The exam accounts for 20% of your total grade.
More informationDependency Parsing. Statistical NLP Fall (Non-)Projectivity. CoNLL Format. Lecture 9: Dependency Parsing
Dependency Parsing Statistical NLP Fall 2016 Lecture 9: Dependency Parsing Slav Petrov Google prep dobj ROOT nsubj pobj det PRON VERB DET NOUN ADP NOUN They solved the problem with statistics CoNLL Format
More informationBringing machine learning & compositional semantics together: central concepts
Bringing machine learning & compositional semantics together: central concepts https://githubcom/cgpotts/annualreview-complearning Chris Potts Stanford Linguistics CS 244U: Natural language understanding
More informationNatural Language Processing CS Lecture 06. Razvan C. Bunescu School of Electrical Engineering and Computer Science
Natural Language Processing CS 6840 Lecture 06 Razvan C. Bunescu School of Electrical Engineering and Computer Science bunescu@ohio.edu Statistical Parsing Define a probabilistic model of syntax P(T S):
More informationMulti-Class Sentiment Classification for Short Text Sequences
Multi-Class Sentiment Classification for Short Text Sequences TIMOTHY LIU KAIHUI SINGAPORE UNIVERSITY OF TECHNOLOGY AND DESIGN What a selfless and courageous hero... Willing to give his life for a total
More informationarxiv: v3 [cs.lg] 14 Jan 2018
A Gentle Tutorial of Recurrent Neural Network with Error Backpropagation Gang Chen Department of Computer Science and Engineering, SUNY at Buffalo arxiv:1610.02583v3 [cs.lg] 14 Jan 2018 1 abstract We describe
More informationa) b) (Natural Language Processing; NLP) (Deep Learning) Bag of words White House RGB [1] IBM
c 1. (Natural Language Processing; NLP) (Deep Learning) RGB IBM 135 8511 5 6 52 yutat@jp.ibm.com a) b) 2. 1 0 2 1 Bag of words White House 2 [1] 2015 4 Copyright c by ORSJ. Unauthorized reproduction of
More informationCS230: Lecture 8 Word2Vec applications + Recurrent Neural Networks with Attention
CS23: Lecture 8 Word2Vec applications + Recurrent Neural Networks with Attention Today s outline We will learn how to: I. Word Vector Representation i. Training - Generalize results with word vectors -
More informationGenerative Models for Sentences
Generative Models for Sentences Amjad Almahairi PhD student August 16 th 2014 Outline 1. Motivation Language modelling Full Sentence Embeddings 2. Approach Bayesian Networks Variational Autoencoders (VAE)
More informationBased on the original slides of Hung-yi Lee
Based on the original slides of Hung-yi Lee Google Trends Deep learning obtains many exciting results. Can contribute to new Smart Services in the Context of the Internet of Things (IoT). IoT Services
More informationOverview Today: From one-layer to multi layer neural networks! Backprop (last bit of heavy math) Different descriptions and viewpoints of backprop
Overview Today: From one-layer to multi layer neural networks! Backprop (last bit of heavy math) Different descriptions and viewpoints of backprop Project Tips Announcement: Hint for PSet1: Understand
More informationLecture 11 Recurrent Neural Networks I
Lecture 11 Recurrent Neural Networks I CMSC 35246: Deep Learning Shubhendu Trivedi & Risi Kondor niversity of Chicago May 01, 2017 Introduction Sequence Learning with Neural Networks Some Sequence Tasks
More informationDegree (k)
0 1 Pr(X k) 0 0 1 Degree (k) Figure A1: Log-log plot of the complementary cumulative distribution function (CCDF) of the degree distribution for a sample month (January 0) network is shown (blue), along
More informationA Deep Learning Model for Structured Outputs with High-order Interaction
A Deep Learning Model for Structured Outputs with High-order Interaction Hongyu Guo, Xiaodan Zhu, Martin Renqiang Min National Research Council of Canada, Ottawa, ON {hongyu.guo, xiaodan.zhu}@nrc-cnrc.gc.ca
More informationTALP at GeoQuery 2007: Linguistic and Geographical Analysis for Query Parsing
TALP at GeoQuery 2007: Linguistic and Geographical Analysis for Query Parsing Daniel Ferrés and Horacio Rodríguez TALP Research Center Software Department Universitat Politècnica de Catalunya {dferres,horacio}@lsi.upc.edu
More informationPrepositional Phrase Attachment over Word Embedding Products
Prepositional Phrase Attachment over Word Embedding Products Pranava Madhyastha (1), Xavier Carreras (2), Ariadna Quattoni (2) (1) University of Sheffield (2) Naver Labs Europe Prepositional Phrases I
More informationIntelligent Systems (AI-2)
Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 19 Oct, 24, 2016 Slide Sources Raymond J. Mooney University of Texas at Austin D. Koller, Stanford CS - Probabilistic Graphical Models D. Page,
More informationStructured Prediction
Structured Prediction Classification Algorithms Classify objects x X into labels y Y First there was binary: Y = {0, 1} Then multiclass: Y = {1,...,6} The next generation: Structured Labels Structured
More informationNLP Homework: Dependency Parsing with Feed-Forward Neural Network
NLP Homework: Dependency Parsing with Feed-Forward Neural Network Submission Deadline: Monday Dec. 11th, 5 pm 1 Background on Dependency Parsing Dependency trees are one of the main representations used
More informationRecurrent Neural Networks. COMP-550 Oct 5, 2017
Recurrent Neural Networks COMP-550 Oct 5, 2017 Outline Introduction to neural networks and deep learning Feedforward neural networks Recurrent neural networks 2 Classification Review y = f( x) output label
More informationDeep Learning for NLP
Deep Learning for NLP Instructor: Wei Xu Ohio State University CSE 5525 Many slides from Greg Durrett Outline Motivation for neural networks Feedforward neural networks Applying feedforward neural networks
More informationParsing. Based on presentations from Chris Manning s course on Statistical Parsing (Stanford)
Parsing Based on presentations from Chris Manning s course on Statistical Parsing (Stanford) S N VP V NP D N John hit the ball Levels of analysis Level Morphology/Lexical POS (morpho-synactic), WSD Elements
More informationPenn Treebank Parsing. Advanced Topics in Language Processing Stephen Clark
Penn Treebank Parsing Advanced Topics in Language Processing Stephen Clark 1 The Penn Treebank 40,000 sentences of WSJ newspaper text annotated with phrasestructure trees The trees contain some predicate-argument
More informationDeep Learning for Natural Language Processing
Deep Learning for Natural Language Processing Dylan Drover, Borui Ye, Jie Peng University of Waterloo djdrover@uwaterloo.ca borui.ye@uwaterloo.ca July 8, 2015 Dylan Drover, Borui Ye, Jie Peng (University
More informationwith Local Dependencies
CS11-747 Neural Networks for NLP Structured Prediction with Local Dependencies Xuezhe Ma (Max) Site https://phontron.com/class/nn4nlp2017/ An Example Structured Prediction Problem: Sequence Labeling Sequence
More informationAspect Term Extraction with History Attention and Selective Transformation 1
Aspect Term Extraction with History Attention and Selective Transformation 1 Xin Li 1, Lidong Bing 2, Piji Li 1, Wai Lam 1, Zhimou Yang 3 Presenter: Lin Ma 2 1 The Chinese University of Hong Kong 2 Tencent
More informationPart-of-Speech Tagging + Neural Networks 3: Word Embeddings CS 287
Part-of-Speech Tagging + Neural Networks 3: Word Embeddings CS 287 Review: Neural Networks One-layer multi-layer perceptron architecture, NN MLP1 (x) = g(xw 1 + b 1 )W 2 + b 2 xw + b; perceptron x is the
More informationlecture 6: modeling sequences (final part)
Natural Language Processing 1 lecture 6: modeling sequences (final part) Ivan Titov Institute for Logic, Language and Computation Outline After a recap: } Few more words about unsupervised estimation of
More informationLearning and Inference over Constrained Output
Learning and Inference over Constrained Output Vasin Punyakanok Dan Roth Wen-tau Yih Dav Zimak Department of Computer Science University of Illinois at Urbana-Champaign {punyakan, danr, yih, davzimak}@uiuc.edu
More informationNaïve Bayes, Maxent and Neural Models
Naïve Bayes, Maxent and Neural Models CMSC 473/673 UMBC Some slides adapted from 3SLP Outline Recap: classification (MAP vs. noisy channel) & evaluation Naïve Bayes (NB) classification Terminology: bag-of-words
More informationHidden Markov Models
Hidden Markov Models Slides mostly from Mitch Marcus and Eric Fosler (with lots of modifications). Have you seen HMMs? Have you seen Kalman filters? Have you seen dynamic programming? HMMs are dynamic
More informationPart of Speech Tagging: Viterbi, Forward, Backward, Forward- Backward, Baum-Welch. COMP-599 Oct 1, 2015
Part of Speech Tagging: Viterbi, Forward, Backward, Forward- Backward, Baum-Welch COMP-599 Oct 1, 2015 Announcements Research skills workshop today 3pm-4:30pm Schulich Library room 313 Start thinking about
More informationNeural networks CMSC 723 / LING 723 / INST 725 MARINE CARPUAT. Slides credit: Graham Neubig
Neural networks CMSC 723 / LING 723 / INST 725 MARINE CARPUAT marine@cs.umd.edu Slides credit: Graham Neubig Outline Perceptron: recap and limitations Neural networks Multi-layer perceptron Forward propagation
More informationNEURAL LANGUAGE MODELS
COMP90042 LECTURE 14 NEURAL LANGUAGE MODELS LANGUAGE MODELS Assign a probability to a sequence of words Framed as sliding a window over the sentence, predicting each word from finite context to left E.g.,
More informationStatistical Machine Learning Theory. From Multi-class Classification to Structured Output Prediction. Hisashi Kashima.
http://goo.gl/jv7vj9 Course website KYOTO UNIVERSITY Statistical Machine Learning Theory From Multi-class Classification to Structured Output Prediction Hisashi Kashima kashima@i.kyoto-u.ac.jp DEPARTMENT
More informationIntroduction to Machine Learning Eran Halperin, Yishay Mansour, Lior Wolf Lecture 13: Applications
Introduction to Machine Learning Eran Halperin, Yishay Mansour, Lior Wolf 2013-2014 Lecture 13: Applications Today Similarity learning ROC curves Probabilistic graphicsl models Neural Networks Cairo
More informationData Mining 2018 Logistic Regression Text Classification
Data Mining 2018 Logistic Regression Text Classification Ad Feelders Universiteit Utrecht Ad Feelders ( Universiteit Utrecht ) Data Mining 1 / 50 Two types of approaches to classification In (probabilistic)
More informationStatistical Machine Learning Theory. From Multi-class Classification to Structured Output Prediction. Hisashi Kashima.
http://goo.gl/xilnmn Course website KYOTO UNIVERSITY Statistical Machine Learning Theory From Multi-class Classification to Structured Output Prediction Hisashi Kashima kashima@i.kyoto-u.ac.jp DEPARTMENT
More informationLecture 5 Neural models for NLP
CS546: Machine Learning in NLP (Spring 2018) http://courses.engr.illinois.edu/cs546/ Lecture 5 Neural models for NLP Julia Hockenmaier juliahmr@illinois.edu 3324 Siebel Center Office hours: Tue/Thu 2pm-3pm
More informationInterpreting Deep Classifiers
Ruprecht-Karls-University Heidelberg Faculty of Mathematics and Computer Science Seminar: Explainable Machine Learning Interpreting Deep Classifiers by Visual Distillation of Dark Knowledge Author: Daniela
More informationLatent Variable Models in NLP
Latent Variable Models in NLP Aria Haghighi with Slav Petrov, John DeNero, and Dan Klein UC Berkeley, CS Division Latent Variable Models Latent Variable Models Latent Variable Models Observed Latent Variable
More informationCSC321 Lecture 16: ResNets and Attention
CSC321 Lecture 16: ResNets and Attention Roger Grosse Roger Grosse CSC321 Lecture 16: ResNets and Attention 1 / 24 Overview Two topics for today: Topic 1: Deep Residual Networks (ResNets) This is the state-of-the
More informationAlgorithms for NLP. Classification II. Taylor Berg-Kirkpatrick CMU Slides: Dan Klein UC Berkeley
Algorithms for NLP Classification II Taylor Berg-Kirkpatrick CMU Slides: Dan Klein UC Berkeley Minimize Training Error? A loss function declares how costly each mistake is E.g. 0 loss for correct label,
More informationUniversität Potsdam Institut für Informatik Lehrstuhl Maschinelles Lernen. Language Models. Tobias Scheffer
Universität Potsdam Institut für Informatik Lehrstuhl Maschinelles Lernen Language Models Tobias Scheffer Stochastic Language Models A stochastic language model is a probability distribution over words.
More informationInformation Extraction from Text
Information Extraction from Text Jing Jiang Chapter 2 from Mining Text Data (2012) Presented by Andrew Landgraf, September 13, 2013 1 What is Information Extraction? Goal is to discover structured information
More informationIntelligent Systems (AI-2)
Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 19 Oct, 23, 2015 Slide Sources Raymond J. Mooney University of Texas at Austin D. Koller, Stanford CS - Probabilistic Graphical Models D. Page,
More informationAsaf Bar Zvi Adi Hayat. Semantic Segmentation
Asaf Bar Zvi Adi Hayat Semantic Segmentation Today s Topics Fully Convolutional Networks (FCN) (CVPR 2015) Conditional Random Fields as Recurrent Neural Networks (ICCV 2015) Gaussian Conditional random
More informationAgainst the F-score. Adam Yedidia. December 8, This essay explains why the F-score is a poor metric for the success of a statistical prediction.
Against the F-score Adam Yedidia December 8, 2016 This essay explains why the F-score is a poor metric for the success of a statistical prediction. 1 What is the F-score? From Wikipedia: In statistical
More informationBetter! Faster! Stronger*!
Jason Eisner Jiarong Jiang He He Better! Faster! Stronger*! Learning to balance accuracy and efficiency when predicting linguistic structures (*theorems) Hal Daumé III UMD CS, UMIACS, Linguistics me@hal3.name
More informationSummarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised
Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised Stefanos Angelidis and Mirella Lapata Institute for Language, Cognition, and Computation School of
More informationGloVe: Global Vectors for Word Representation 1
GloVe: Global Vectors for Word Representation 1 J. Pennington, R. Socher, C.D. Manning M. Korniyenko, S. Samson Deep Learning for NLP, 13 Jun 2017 1 https://nlp.stanford.edu/projects/glove/ Outline Background
More informationNatural Language Processing
SFU NatLangLab Natural Language Processing Anoop Sarkar anoopsarkar.github.io/nlp-class Simon Fraser University October 9, 2018 0 Natural Language Processing Anoop Sarkar anoopsarkar.github.io/nlp-class
More informationDeep Learning Sequence to Sequence models: Attention Models. 17 March 2018
Deep Learning Sequence to Sequence models: Attention Models 17 March 2018 1 Sequence-to-sequence modelling Problem: E.g. A sequence X 1 X N goes in A different sequence Y 1 Y M comes out Speech recognition:
More informationChapter Finding parse trees
Chapter 16 NP Some tasks definitely require exponential time. That is, we can not only display an exponential-time algorithm, but we can also prove that the problem cannot be solved in anything less than
More informationDeep Learning for NLP
Deep Learning for NLP CS224N Christopher Manning (Many slides borrowed from ACL 2012/NAACL 2013 Tutorials by me, Richard Socher and Yoshua Bengio) Machine Learning and NLP NER WordNet Usually machine learning
More informationAssignment 1. Learning distributed word representations. Jimmy Ba
Assignment 1 Learning distributed word representations Jimmy Ba csc321ta@cstorontoedu Background Text and language play central role in a wide range of computer science and engineering problems Applications
More informationMagic Of The Moonlight (Full Moon) By Ellen Schreiber
Magic Of The Moonlight (Full Moon) By Ellen Schreiber While most of this film will just go over your head as far as caring about the deep voabulary used to explain characters, "Magic in the Moonlight"
More informationDeep Learning for NLP Part 2
Deep Learning for NLP Part 2 CS224N Christopher Manning (Many slides borrowed from ACL 2012/NAACL 2013 Tutorials by me, Richard Socher and Yoshua Bengio) 2 Part 1.3: The Basics Word Representations The
More information11/3/15. Deep Learning for NLP. Deep Learning and its Architectures. What is Deep Learning? Advantages of Deep Learning (Part 1)
11/3/15 Machine Learning and NLP Deep Learning for NLP Usually machine learning works well because of human-designed representations and input features CS224N WordNet SRL Parser Machine learning becomes
More informationRepresenting structured relational data in Euclidean vector spaces. Tony Plate
Representing structured relational data in Euclidean vector spaces Tony Plate tplate@acm.org http://www.d-reps.org October 2004 AAAI Symposium 2004 1 Overview A general method for representing structured
More informationMachine Learning for natural language processing
Machine Learning for natural language processing Classification: Maximum Entropy Models Laura Kallmeyer Heinrich-Heine-Universität Düsseldorf Summer 2016 1 / 24 Introduction Classification = supervised
More informationIN FALL NATURAL LANGUAGE PROCESSING. Jan Tore Lønning
1 IN4080 2018 FALL NATURAL LANGUAGE PROCESSING Jan Tore Lønning 2 Logistic regression Lecture 8, 26 Sept Today 3 Recap: HMM-tagging Generative and discriminative classifiers Linear classifiers Logistic
More informationECE521 Lecture 7/8. Logistic Regression
ECE521 Lecture 7/8 Logistic Regression Outline Logistic regression (Continue) A single neuron Learning neural networks Multi-class classification 2 Logistic regression The output of a logistic regression
More informationStatistical NLP for the Web
Statistical NLP for the Web Neural Networks, Deep Belief Networks Sameer Maskey Week 8, October 24, 2012 *some slides from Andrew Rosenberg Announcements Please ask HW2 related questions in courseworks
More informationVine Pruning for Efficient Multi-Pass Dependency Parsing. Alexander M. Rush and Slav Petrov
Vine Pruning for Efficient Multi-Pass Dependency Parsing Alexander M. Rush and Slav Petrov Dependency Parsing Styles of Dependency Parsing greedy O(n) transition-based parsers (Nivre 2004) graph-based
More informationBEYOND WORD IMPORTANCE: CONTEXTUAL DE-
BEYOND WORD IMPORTANCE: CONTEXTUAL DE- COMPOSITION TO EXTRACT INTERACTIONS FROM LSTMS W. James Murdoch Department of Statistics University of California, Berkeley jmurdoch@berkeley.edu Peter J. Liu Google
More informationContext-Free Parsing: CKY & Earley Algorithms and Probabilistic Parsing
Context-Free Parsing: CKY & Earley Algorithms and Probabilistic Parsing Natural Language Processing CS 4120/6120 Spring 2017 Northeastern University David Smith with some slides from Jason Eisner & Andrew
More informationHidden Markov Models
CS 2750: Machine Learning Hidden Markov Models Prof. Adriana Kovashka University of Pittsburgh March 21, 2016 All slides are from Ray Mooney Motivating Example: Part Of Speech Tagging Annotate each word
More information