Better! Faster! Stronger*!
|
|
- Debra Nelson
- 6 years ago
- Views:
Transcription
1 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,
2 2 Hal Daumé III NLP as transduction Task Input Output Machine Translation Document Summarization Ces deux principes se tiennent à la croisée de la philosophie, de la politique, de l économie, de la sociologie et du droit. Argentina was still obsessed with the Falkland Islands even in 1994, 12 years after its defeat in the 74-day war with Britain. The country's overriding foreign policy aim continued to be winning sovereignty over the islands. Both principles lie at the crossroads of philosophy, politics, economics, sociology, and law. The Falkland islands war, in 1982, was fought between Britain and Argentina. Syntactic Analysis...many more... The man ate a big sandwich. The man ate a big sandwich
3 3 Hal Daumé III Why are complex predictions slow? Parsing # trees ~ O(2 sentence ) Translation # trans ~ O(2 foreign x english ) Summarization # sums ~ O(2 document ) Concretely, n 3 = grammar = ½ million What about dynamic programming...? Often not possible (features are too complicated) Even when possible, polynomial-time is too painful: Parsing is O( grammar x sentence 3 ) but grammar is
4 4 Hal Daumé III Case study: prioritized parsing 2500 Time (seconds) minutes 10 minutes 0 1 minute Sentence Length
5 5 Hal Daumé III Case study: prioritized parsing 2500 Time (seconds) minutes 10 minutes S VP NP VP NP Pro Aux Vrb Noun Output Input 0 1 minute Sentence Length
6 6 Hal Daumé III Learning to be fast! Training Data Hand-built Heuristics Fancy Learning Algorithm Fancier Learning Slow Predictor Algorithm Fast Predictor Quality = tradeoff(accuracy, time)
7 Prioritized search (eg., parsing) S VP NP VP NP Pro Aux Vrb Noun NP Aux Vrb NP Hal Daumé III (me@hal3.name) 7 VP[2,4] 2 VP[1,3] 1 S[0,2] (Jiang+Teichert+Eisner+D, NIPS 2012)
8 Prioritized search (eg., parsing) S VP NP VP NP Pro Aux Vrb Noun NP Aux Vrb NP Hal Daumé III (me@hal3.name) 7 VP[2,4] 2 VP[1,3] 1 S[0,2] (Jiang+Teichert+Eisner+D, NIPS 2012)
9 Prioritized search (eg., parsing) S VP NP VP NP Pro Aux Vrb Noun VP NP Aux Vrb NP Hal Daumé III (me@hal3.name) 2 VP[1,3] 2 VP[1,4] 1 S[0,2] (Jiang+Teichert+Eisner+D, NIPS 2012)
10 Prioritized search (eg., parsing) S VP NP VP NP Pro Aux Vrb Noun VP VP NP Aux Vrb NP Hal Daumé III (me@hal3.name) 2 VP[1,4] 1 S[1,3] 1 S[0,2] (Jiang+Teichert+Eisner+D, NIPS 2012)
11 Prioritized search (eg., parsing) S VP NP VP NP Pro Aux Vrb Noun VP VP VP NP Aux Vrb NP Hal Daumé III (me@hal3.name) 5 S[0,4] 1 S[1,3] 1 S[0,2] (Jiang+Teichert+Eisner+D, NIPS 2012)
12 Prioritized search (eg., parsing) S VP NP VP NP Pro Aux Vrb Noun S VP VP VP NP Aux Vrb NP Hal Daumé III (me@hal3.name) 9 stop 1 S[1,3] 1 S[0,2] (Jiang+Teichert+Eisner+D, NIPS 2012)
13 What do better priorities buy us? Ideally, run until queue is empty Ordering only matters because you want to: Only pop items that have a real impact on result Avoid premature pops Stop early Goal: learn a priority function that optimizes accuracy/speed trade-off Typical solution: hand-built heuristics 13 Hal Daumé III (me@hal3.name) User parameter Our solution: learning to optimize accuracy - λ time (Jiang+Teichert+Eisner+D, NIPS 2012)
14 Prioritized search (eg., parsing) S Learning a heuristic: VP priority(x) = θ φ(chart, item) NP VP NP Example features: Inside score of VP Are 2 word VPs good? p(vp I) and p(cans VP) Could VP combine with NP? VP compete with other spans? Crossing constituents? Pro Aux Vrb Noun VP NP Aux Vrb NP Hal Daumé III (me@hal3.name) 2 VP[1,3] 2 VP[1,4] 1 S[0,2] (Jiang+Teichert+Eisner+D, NIPS 2012)
15 15 Hal Daumé III Learning priorities S VP NP VP NP Pro Aux Vrb Noun Challenges: The world is non-deterministic State space is huge (25 words 5x1014 states) The oracle is way too good (25 actions vs 25k actions) VP The oracle does not experience NP Aux Vrb NP a trade-off between speed and accuracy VP[1,3] 2 VP[1,4] 1 S[0,2] Pssst! You should choose the 2 nd one!
16 16 Hal Daumé III Parsing Trajectories (I) Policy Gradient Trajectories Ground Truth Trajectories (Oracle Trajectories)
17 17 Hal Daumé III Preliminary Result Method Recall Relative # of pops Apprenticeship Learning x with Reward Shaping x Policy Gradient with Boltzmann Exploration x Uniform cost search x Pruned Uniform cost search x Failure Causes: Too hard to imitate the oracle with our features!
18 18 Hal Daumé III Parsing Trajectories (II) Policy Gradient Trajectories Oracle Trajectori Good Trajectories Oracle-Infused Trajectories
19 19 Hal Daumé III Oracle-Infused Policy Gradient Method Recall Relative # of pops Oracle-Infused Policy Gradient x Apprenticeship Learning x with Reward Shaping x Policy Gradient with Boltzmann Exploration x Uniform cost search x Pruned Uniform cost search x
20 20 Hal Daumé III Pareto Frontier Has access to multiple levels of grammar Multiple pruning thresholds
21 take away messages... Many AI tasks can be cast as prioritized search (parsing, planning, inference...) Non-determinism is a unique property of such sequential decision making processes Allows us to reason about trajectories, and learn to trade speed for accuracy
22 22 Hal Daumé III Dependency parsing [root] object n-mod n-mod subject n-mod p-mod n-mod NLP algorithms use a kitchen sink of features
23 23 Hal Daumé III Dependency parsing [root] NLP algorithms use a kitchen sink of features
24 Dependency parsing algorithms use a kitchen NLP sink features 24 Hal Daumé III (me@hal3.name) of
25 Dependency parsing algorithms Edge Features: Lex(use sink) POS(verb noun) skip(2) skip(det) NL skip(noun) P skip(det Noun) dist=3 various regexps... spelling features etc... use Three steps: 1. Compute POS tags 2. Compute kn 2 features 3. Run directed MST features 25 Hal Daumé III (me@hal3.name) a of kitchen sink
26 26 Hal Daumé III Case study: dependency parsing Time (seconds) Average Sentence <10 <20 <30 <40 <50 >=50 Sentence Length 0.12 Tagging Features Parsing
27 27 Hal Daumé III Dynamic feature selection
28 The oracle too good! The oracle knows the label Picks feature with highest y*value*weight 90% Ends after selecting one feature Coach says how to improve, not the best thing to do Pssst! You should choose argmin E[l(a)] a Overall accuracy If N = T log T, L(π n ) < T N + O(1) for some n Provably smaller than DAgger's epsilon! 28 Hal Daumé III (me@hal3.name) 80% Pssst! You should choose argmin E[l(a)] η f(a) a 70% Oracle Coaching DAgger Forward selection Average cost/example (He+Eisner+D, NIPS 2012)
29 29 Hal Daumé III Results across languages
30 Jason Eisner Jiarong Jiang We can build systems that learn to trade-off speed vs accuracy (it's hard) Requires new algorithms Important to model the problem right Adam Teichert He He Tim Vieira I'm going to be on the job market soon! Imitation/reinforcement learning applied to non-deterministic search Orthogonal improvements to most speedup type papers Thanks! Questions?
imitation learning Recurrent Hal Daumé III University of
Networks imitation learning Recurrent Neural Hal Daumé III University of Maryland me@hal3.name @haldaume3 Networks imitation learning Recurrent Neural NON-DIFFERENTIABLE DISCONTINUOUS Hal Daumé III University
More informationThe Noisy Channel Model and Markov Models
1/24 The Noisy Channel Model and Markov Models Mark Johnson September 3, 2014 2/24 The big ideas The story so far: machine learning classifiers learn a function that maps a data item X to a label Y handle
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 informationImitation Learning by Coaching. Abstract
Imitation Learning by Coaching He He Hal Daumé III Department of Computer Science University of Maryland College Park, MD 20740 {hhe,hal}@cs.umd.edu Abstract Jason Eisner Department of Computer Science
More informationStatistical Machine Translation
Statistical Machine Translation -tree-based models (cont.)- Artem Sokolov Computerlinguistik Universität Heidelberg Sommersemester 2015 material from P. Koehn, S. Riezler, D. Altshuler Bottom-Up Decoding
More informationConditional Language modeling with attention
Conditional Language modeling with attention 2017.08.25 Oxford Deep NLP 조수현 Review Conditional language model: assign probabilities to sequence of words given some conditioning context x What is the probability
More informationLab 12: Structured Prediction
December 4, 2014 Lecture plan structured perceptron application: confused messages application: dependency parsing structured SVM Class review: from modelization to classification What does learning mean?
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 informationLECTURER: BURCU CAN Spring
LECTURER: BURCU CAN 2017-2018 Spring Regular Language Hidden Markov Model (HMM) Context Free Language Context Sensitive Language Probabilistic Context Free Grammar (PCFG) Unrestricted Language PCFGs can
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 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 information13A. Computational Linguistics. 13A. Log-Likelihood Dependency Parsing. CSC 2501 / 485 Fall 2017
Computational Linguistics CSC 2501 / 485 Fall 2017 13A 13A. Log-Likelihood Dependency Parsing Gerald Penn Department of Computer Science, University of Toronto Based on slides by Yuji Matsumoto, Dragomir
More informationSpectral Unsupervised Parsing with Additive Tree Metrics
Spectral Unsupervised Parsing with Additive Tree Metrics Ankur Parikh, Shay Cohen, Eric P. Xing Carnegie Mellon, University of Edinburgh Ankur Parikh 2014 1 Overview Model: We present a novel approach
More informationNatural Language Processing
SFU NatLangLab Natural Language Processing Anoop Sarkar anoopsarkar.github.io/nlp-class Simon Fraser University September 27, 2018 0 Natural Language Processing Anoop Sarkar anoopsarkar.github.io/nlp-class
More informationTuning as Linear Regression
Tuning as Linear Regression Marzieh Bazrafshan, Tagyoung Chung and Daniel Gildea Department of Computer Science University of Rochester Rochester, NY 14627 Abstract We propose a tuning method for statistical
More informationCS 662 Sample Midterm
Name: 1 True/False, plus corrections CS 662 Sample Midterm 35 pts, 5 pts each Each of the following statements is either true or false. If it is true, mark it true. If it is false, correct the statement
More informationA* Search. 1 Dijkstra Shortest Path
A* Search Consider the eight puzzle. There are eight tiles numbered 1 through 8 on a 3 by three grid with nine locations so that one location is left empty. We can move by sliding a tile adjacent to the
More informationProbabilistic Context-free Grammars
Probabilistic Context-free Grammars Computational Linguistics Alexander Koller 24 November 2017 The CKY Recognizer S NP VP NP Det N VP V NP V ate NP John Det a N sandwich i = 1 2 3 4 k = 2 3 4 5 S NP John
More informationA Supertag-Context Model for Weakly-Supervised CCG Parser Learning
A Supertag-Context Model for Weakly-Supervised CCG Parser Learning Dan Garrette Chris Dyer Jason Baldridge Noah A. Smith U. Washington CMU UT-Austin CMU Contributions 1. A new generative model for learning
More informationLinear Classifiers IV
Universität Potsdam Institut für Informatik Lehrstuhl Linear Classifiers IV Blaine Nelson, Tobias Scheffer Contents Classification Problem Bayesian Classifier Decision Linear Classifiers, MAP Models Logistic
More informationS NP VP 0.9 S VP 0.1 VP V NP 0.5 VP V 0.1 VP V PP 0.1 NP NP NP 0.1 NP NP PP 0.2 NP N 0.7 PP P NP 1.0 VP NP PP 1.0. N people 0.
/6/7 CS 6/CS: Natural Language Processing Instructor: Prof. Lu Wang College of Computer and Information Science Northeastern University Webpage: www.ccs.neu.edu/home/luwang The grammar: Binary, no epsilons,.9..5
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 informationOutline. Parsing. Approximations Some tricks Learning agenda-based parsers
Outline Parsing CKY Approximations Some tricks Learning agenda-based parsers 0 Parsing We need to compute compute argmax d D(x) p θ (d x) Inference: Find best tree given model 1 Parsing We need to compute
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 informationChunking with Support Vector Machines
NAACL2001 Chunking with Support Vector Machines Graduate School of Information Science, Nara Institute of Science and Technology, JAPAN Taku Kudo, Yuji Matsumoto {taku-ku,matsu}@is.aist-nara.ac.jp Chunking
More informationAN ABSTRACT OF THE DISSERTATION OF
AN ABSTRACT OF THE DISSERTATION OF Kai Zhao for the degree of Doctor of Philosophy in Computer Science presented on May 30, 2017. Title: Structured Learning with Latent Variables: Theory and Algorithms
More informationMultiword Expression Identification with Tree Substitution Grammars
Multiword Expression Identification with Tree Substitution Grammars Spence Green, Marie-Catherine de Marneffe, John Bauer, and Christopher D. Manning Stanford University EMNLP 2011 Main Idea Use syntactic
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 informationLog-Linear Models, MEMMs, and CRFs
Log-Linear Models, MEMMs, and CRFs Michael Collins 1 Notation Throughout this note I ll use underline to denote vectors. For example, w R d will be a vector with components w 1, w 2,... w d. We use expx
More informationDialogue Systems. Statistical NLU component. Representation. A Probabilistic Dialogue System. Task: map a sentence + context to a database query
Statistical NLU component Task: map a sentence + context to a database query Dialogue Systems User: Show me flights from NY to Boston, leaving tomorrow System: [returns a list of flights] Origin (City
More informationNatural Language Processing : Probabilistic Context Free Grammars. Updated 5/09
Natural Language Processing : Probabilistic Context Free Grammars Updated 5/09 Motivation N-gram models and HMM Tagging only allowed us to process sentences linearly. However, even simple sentences require
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 informationOverview of Statistical Tools. Statistical Inference. Bayesian Framework. Modeling. Very simple case. Things are usually more complicated
Fall 3 Computer Vision Overview of Statistical Tools Statistical Inference Haibin Ling Observation inference Decision Prior knowledge http://www.dabi.temple.edu/~hbling/teaching/3f_5543/index.html Bayesian
More informationMarrying Dynamic Programming with Recurrent Neural Networks
Marrying Dynamic Programming with Recurrent Neural Networks I eat sushi with tuna from Japan Liang Huang Oregon State University Structured Prediction Workshop, EMNLP 2017, Copenhagen, Denmark Marrying
More informationDynamic Programming: Hidden Markov Models
University of Oslo : Department of Informatics Dynamic Programming: Hidden Markov Models Rebecca Dridan 16 October 2013 INF4820: Algorithms for AI and NLP Topics Recap n-grams Parts-of-speech Hidden Markov
More informationGrammars and introduction to machine learning. Computers Playing Jeopardy! Course Stony Brook University
Grammars and introduction to machine learning Computers Playing Jeopardy! Course Stony Brook University Last class: grammars and parsing in Prolog Noun -> roller Verb thrills VP Verb NP S NP VP NP S VP
More informationParsing with CFGs L445 / L545 / B659. Dept. of Linguistics, Indiana University Spring Parsing with CFGs. Direction of processing
L445 / L545 / B659 Dept. of Linguistics, Indiana University Spring 2016 1 / 46 : Overview Input: a string Output: a (single) parse tree A useful step in the process of obtaining meaning We can view the
More informationParsing with CFGs. Direction of processing. Top-down. Bottom-up. Left-corner parsing. Chart parsing CYK. Earley 1 / 46.
: Overview L545 Dept. of Linguistics, Indiana University Spring 2013 Input: a string Output: a (single) parse tree A useful step in the process of obtaining meaning We can view the problem as searching
More informationLagrangian Relaxation Algorithms for Inference in Natural Language Processing
Lagrangian Relaxation Algorithms for Inference in Natural Language Processing Alexander M. Rush and Michael Collins (based on joint work with Yin-Wen Chang, Tommi Jaakkola, Terry Koo, Roi Reichart, David
More informationCS460/626 : Natural Language
CS460/626 : Natural Language Processing/Speech, NLP and the Web (Lecture 27 SMT Assignment; HMM recap; Probabilistic Parsing cntd) Pushpak Bhattacharyya CSE Dept., IIT Bombay 17 th March, 2011 CMU Pronunciation
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 informationCS : Speech, NLP and the Web/Topics in AI
CS626-449: Speech, NLP and the Web/Topics in AI Pushpak Bhattacharyya CSE Dept., IIT Bombay Lecture-17: Probabilistic parsing; insideoutside probabilities Probability of a parse tree (cont.) S 1,l NP 1,2
More informationStatistical Methods for NLP
Statistical Methods for NLP Stochastic Grammars Joakim Nivre Uppsala University Department of Linguistics and Philology joakim.nivre@lingfil.uu.se Statistical Methods for NLP 1(22) Structured Classification
More informationTransition-Based Parsing
Transition-Based Parsing Based on atutorial at COLING-ACL, Sydney 2006 with Joakim Nivre Sandra Kübler, Markus Dickinson Indiana University E-mail: skuebler,md7@indiana.edu Transition-Based Parsing 1(11)
More informationSoft Inference and Posterior Marginals. September 19, 2013
Soft Inference and Posterior Marginals September 19, 2013 Soft vs. Hard Inference Hard inference Give me a single solution Viterbi algorithm Maximum spanning tree (Chu-Liu-Edmonds alg.) Soft inference
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 informationDecoding and Inference with Syntactic Translation Models
Decoding and Inference with Syntactic Translation Models March 5, 2013 CFGs S NP VP VP NP V V NP NP CFGs S NP VP S VP NP V V NP NP CFGs S NP VP S VP NP V NP VP V NP NP CFGs S NP VP S VP NP V NP VP V NP
More informationNatural Language Processing
Natural Language Processing Info 159/259 Lecture 12: Features and hypothesis tests (Oct 3, 2017) David Bamman, UC Berkeley Announcements No office hours for DB this Friday (email if you d like to chat)
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 informationAdvanced Natural Language Processing Syntactic Parsing
Advanced Natural Language Processing Syntactic Parsing Alicia Ageno ageno@cs.upc.edu Universitat Politècnica de Catalunya NLP statistical parsing 1 Parsing Review Statistical Parsing SCFG Inside Algorithm
More informationProcessing/Speech, NLP and the Web
CS460/626 : Natural Language Processing/Speech, NLP and the Web (Lecture 25 Probabilistic Parsing) Pushpak Bhattacharyya CSE Dept., IIT Bombay 14 th March, 2011 Bracketed Structure: Treebank Corpus [ S1[
More informationCS261: A Second Course in Algorithms Lecture #12: Applications of Multiplicative Weights to Games and Linear Programs
CS26: A Second Course in Algorithms Lecture #2: Applications of Multiplicative Weights to Games and Linear Programs Tim Roughgarden February, 206 Extensions of the Multiplicative Weights Guarantee Last
More informationCITS4211 Mid-semester test 2011
CITS4211 Mid-semester test 2011 Fifty minutes, answer all four questions, total marks 60 Question 1. (12 marks) Briefly describe the principles, operation, and performance issues of iterative deepening.
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 informationMaschinelle Sprachverarbeitung
Maschinelle Sprachverarbeitung Parsing with Probabilistic Context-Free Grammar Ulf Leser Content of this Lecture Phrase-Structure Parse Trees Probabilistic Context-Free Grammars Parsing with PCFG Other
More informationMaschinelle Sprachverarbeitung
Maschinelle Sprachverarbeitung Parsing with Probabilistic Context-Free Grammar Ulf Leser Content of this Lecture Phrase-Structure Parse Trees Probabilistic Context-Free Grammars Parsing with PCFG Other
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 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 informationAspects of Tree-Based Statistical Machine Translation
Aspects of Tree-Based Statistical Machine Translation Marcello Federico Human Language Technology FBK 2014 Outline Tree-based translation models: Synchronous context free grammars Hierarchical phrase-based
More informationHierarchical Bayesian Nonparametrics
Hierarchical Bayesian Nonparametrics Micha Elsner April 11, 2013 2 For next time We ll tackle a paper: Green, de Marneffe, Bauer and Manning: Multiword Expression Identification with Tree Substitution
More informationDeep 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 informationQuasi-Synchronous Phrase Dependency Grammars for Machine Translation. lti
Quasi-Synchronous Phrase Dependency Grammars for Machine Translation Kevin Gimpel Noah A. Smith 1 Introduction MT using dependency grammars on phrases Phrases capture local reordering and idiomatic translations
More informationCutting Plane Training of Structural SVM
Cutting Plane Training of Structural SVM Seth Neel University of Pennsylvania sethneel@wharton.upenn.edu September 28, 2017 Seth Neel (Penn) Short title September 28, 2017 1 / 33 Overview Structural SVMs
More informationReview. Earley Algorithm Chapter Left Recursion. Left-Recursion. Rule Ordering. Rule Ordering
Review Earley Algorithm Chapter 13.4 Lecture #9 October 2009 Top-Down vs. Bottom-Up Parsers Both generate too many useless trees Combine the two to avoid over-generation: Top-Down Parsing with Bottom-Up
More informationStatistical Machine Translation. Part III: Search Problem. Complexity issues. DP beam-search: with single and multi-stacks
Statistical Machine Translation Marcello Federico FBK-irst Trento, Italy Galileo Galilei PhD School - University of Pisa Pisa, 7-19 May 008 Part III: Search Problem 1 Complexity issues A search: with single
More informationCMPT-825 Natural Language Processing. Why are parsing algorithms important?
CMPT-825 Natural Language Processing Anoop Sarkar http://www.cs.sfu.ca/ anoop October 26, 2010 1/34 Why are parsing algorithms important? A linguistic theory is implemented in a formal system to generate
More informationApplied Natural Language Processing
Applied Natural Language Processing Info 256 Lecture 7: Testing (Feb 12, 2019) David Bamman, UC Berkeley Significance in NLP You develop a new method for text classification; is it better than what comes
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 informationComputational Linguistics
Computational Linguistics Dependency-based Parsing Clayton Greenberg Stefan Thater FR 4.7 Allgemeine Linguistik (Computerlinguistik) Universität des Saarlandes Summer 2016 Acknowledgements These slides
More informationSyntax-Based Decoding
Syntax-Based Decoding Philipp Koehn 9 November 2017 1 syntax-based models Synchronous Context Free Grammar Rules 2 Nonterminal rules NP DET 1 2 JJ 3 DET 1 JJ 3 2 Terminal rules N maison house NP la maison
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 informationAlgorithms for Syntax-Aware Statistical Machine Translation
Algorithms for Syntax-Aware Statistical Machine Translation I. Dan Melamed, Wei Wang and Ben Wellington ew York University Syntax-Aware Statistical MT Statistical involves machine learning (ML) seems crucial
More informationECS289: Scalable Machine Learning
ECS289: Scalable Machine Learning Cho-Jui Hsieh UC Davis Oct 18, 2016 Outline One versus all/one versus one Ranking loss for multiclass/multilabel classification Scaling to millions of labels Multiclass
More informationCS 6120/CS4120: Natural Language Processing
CS 6120/CS4120: Natural Language Processing Instructor: Prof. Lu Wang College of Computer and Information Science Northeastern University Webpage: www.ccs.neu.edu/home/luwang Assignment/report submission
More informationThe Greedy Method. Design and analysis of algorithms Cs The Greedy Method
Design and analysis of algorithms Cs 3400 The Greedy Method 1 Outline and Reading The Greedy Method Technique Fractional Knapsack Problem Task Scheduling 2 The Greedy Method Technique The greedy method
More informationACS Introduction to NLP Lecture 2: Part of Speech (POS) Tagging
ACS Introduction to NLP Lecture 2: Part of Speech (POS) Tagging Stephen Clark Natural Language and Information Processing (NLIP) Group sc609@cam.ac.uk The POS Tagging Problem 2 England NNP s POS fencers
More informationEcient Higher-Order CRFs for Morphological Tagging
Ecient Higher-Order CRFs for Morphological Tagging Thomas Müller, Helmut Schmid and Hinrich Schütze Center for Information and Language Processing University of Munich Outline 1 Contributions 2 Motivation
More informationComputational Linguistics. Acknowledgements. Phrase-Structure Trees. Dependency-based Parsing
Computational Linguistics Dependency-based Parsing Dietrich Klakow & Stefan Thater FR 4.7 Allgemeine Linguistik (Computerlinguistik) Universität des Saarlandes Summer 2013 Acknowledgements These slides
More informationNatural Language Processing. Slides from Andreas Vlachos, Chris Manning, Mihai Surdeanu
Natural Language Processing Slides from Andreas Vlachos, Chris Manning, Mihai Surdeanu Projects Project descriptions due today! Last class Sequence to sequence models Attention Pointer networks Today Weak
More informationDoctoral Course in Speech Recognition. May 2007 Kjell Elenius
Doctoral Course in Speech Recognition May 2007 Kjell Elenius CHAPTER 12 BASIC SEARCH ALGORITHMS State-based search paradigm Triplet S, O, G S, set of initial states O, set of operators applied on a state
More informationMarkov Decision Processes Chapter 17. Mausam
Markov Decision Processes Chapter 17 Mausam Planning Agent Static vs. Dynamic Fully vs. Partially Observable Environment What action next? Deterministic vs. Stochastic Perfect vs. Noisy Instantaneous vs.
More informationNeural Networks 2. 2 Receptive fields and dealing with image inputs
CS 446 Machine Learning Fall 2016 Oct 04, 2016 Neural Networks 2 Professor: Dan Roth Scribe: C. Cheng, C. Cervantes Overview Convolutional Neural Networks Recurrent Neural Networks 1 Introduction There
More informationMultilevel Coarse-to-Fine PCFG Parsing
Multilevel Coarse-to-Fine PCFG Parsing Eugene Charniak, Mark Johnson, Micha Elsner, Joseph Austerweil, David Ellis, Isaac Haxton, Catherine Hill, Shrivaths Iyengar, Jeremy Moore, Michael Pozar, and Theresa
More informationCS 446 Machine Learning Fall 2016 Nov 01, Bayesian Learning
CS 446 Machine Learning Fall 206 Nov 0, 206 Bayesian Learning Professor: Dan Roth Scribe: Ben Zhou, C. Cervantes Overview Bayesian Learning Naive Bayes Logistic Regression Bayesian Learning So far, we
More informationComputational Models - Lecture 4
Computational Models - Lecture 4 Regular languages: The Myhill-Nerode Theorem Context-free Grammars Chomsky Normal Form Pumping Lemma for context free languages Non context-free languages: Examples Push
More informationPAC Generalization Bounds for Co-training
PAC Generalization Bounds for Co-training Sanjoy Dasgupta AT&T Labs Research dasgupta@research.att.com Michael L. Littman AT&T Labs Research mlittman@research.att.com David McAllester AT&T Labs Research
More informationParsing. A Parsing. Laura Kallmeyer. Winter 2017/18. Heinrich-Heine-Universität Düsseldorf 1 / 27
Parsing A Parsing Laura Kallmeyer Heinrich-Heine-Universität Düsseldorf Winter 2017/18 1 / 27 Table of contents 1 Introduction 2 A parsing 3 Computation of the SX estimates 4 Parsing with the SX estimate
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 informationA FUZZY NEURAL NETWORK MODEL FOR FORECASTING STOCK PRICE
A FUZZY NEURAL NETWORK MODEL FOR FORECASTING STOCK PRICE Li Sheng Institute of intelligent information engineering Zheiang University Hangzhou, 3007, P. R. China ABSTRACT In this paper, a neural network-driven
More informationAn introduction to PRISM and its applications
An introduction to PRISM and its applications Yoshitaka Kameya Tokyo Institute of Technology 2007/9/17 FJ-2007 1 Contents What is PRISM? Two examples: from population genetics from statistical natural
More informationCS 570: Machine Learning Seminar. Fall 2016
CS 570: Machine Learning Seminar Fall 2016 Class Information Class web page: http://web.cecs.pdx.edu/~mm/mlseminar2016-2017/fall2016/ Class mailing list: cs570@cs.pdx.edu My office hours: T,Th, 2-3pm or
More informationGraph-based Dependency Parsing. Ryan McDonald Google Research
Graph-based Dependency Parsing Ryan McDonald Google Research ryanmcd@google.com Reader s Digest Graph-based Dependency Parsing Ryan McDonald Google Research ryanmcd@google.com root ROOT Dependency Parsing
More informationLecture 12: Algorithms for HMMs
Lecture 12: Algorithms for HMMs Nathan Schneider (some slides from Sharon Goldwater; thanks to Jonathan May for bug fixes) ENLP 17 October 2016 updated 9 September 2017 Recap: tagging POS tagging is a
More informationStatistical Methods for NLP
Statistical Methods for NLP Sequence Models Joakim Nivre Uppsala University Department of Linguistics and Philology joakim.nivre@lingfil.uu.se Statistical Methods for NLP 1(21) Introduction Structured
More informationFeedforward Neural Networks
Feedforward Neural Networks Michael Collins 1 Introduction In the previous notes, we introduced an important class of models, log-linear models. In this note, we describe feedforward neural networks, which
More informationOptimization and Complexity
Optimization and Complexity Decision Systems Group Brigham and Women s Hospital, Harvard Medical School Harvard-MIT Division of Health Sciences and Technology Aim Give you an intuition of what is meant
More informationCS260: Machine Learning Algorithms
CS260: Machine Learning Algorithms Lecture 4: Stochastic Gradient Descent Cho-Jui Hsieh UCLA Jan 16, 2019 Large-scale Problems Machine learning: usually minimizing the training loss min w { 1 N min w {
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 informationLinear Regression. Aarti Singh. Machine Learning / Sept 27, 2010
Linear Regression Aarti Singh Machine Learning 10-701/15-781 Sept 27, 2010 Discrete to Continuous Labels Classification Sports Science News Anemic cell Healthy cell Regression X = Document Y = Topic X
More informationLecture 15. Probabilistic Models on Graph
Lecture 15. Probabilistic Models on Graph Prof. Alan Yuille Spring 2014 1 Introduction We discuss how to define probabilistic models that use richly structured probability distributions and describe how
More information