Vine Pruning for Efficient Multi-Pass Dependency Parsing. Alexander M. Rush and Slav Petrov
|
|
- Beverly Lawson
- 5 years ago
- Views:
Transcription
1 Vine Pruning for Efficient Multi-Pass Dependency Parsing Alexander M. Rush and Slav Petrov
2 Dependency Parsing
3 Styles of Dependency Parsing greedy O(n) transition-based parsers (Nivre 2004) graph-based parsers (Eisner 2000) (McDonald 2005) speed first-order O(n 3 ) k-best O(kn) second-order O(n 3 ) accuracy third-order O(n 4 )
4 Styles of Dependency Parsing greedy O(n) transition-based parsers (Nivre 2004) graph-based parsers (Eisner 2000) (McDonald 2005) speed first-order O(n 3 ) k-best O(kn) second-order O(n 3 ) accuracy this work third-order O(n 4 )
5 Preview: Coarse-to-Fine Cascades cgwire vine first second
6 linear-size dependency representation
7 Representation Heads Modifiers
8 Representation Heads Modifiers
9 Representation Heads Modifiers
10 Representation Heads Modifiers
11 Representation Heads Modifiers
12 Representation Heads Modifiers
13 Representation Heads Modifiers
14 Representation Heads Modifiers
15 First-Order Feature Calculation
16 First-Order Feature Calculation [] [VBD] [] [ADP] [] [VERB] [] [IN] [ VBD] [ ADP] [ ] [VBD ADP] [ VERB] [ IN] [ ] [VERB IN] [VBD ADP] [ ADP] [ VBD ADP] [ VBD ] [ADJ ADP] [VBD ADP] [VBD ADJ ADP] [VBD ADJ ] [NNS ADP] [NNS VBD ADP] [NNS VBD ] [ADJ ADP NNP] [VBD ADP NNP] [VBD ADJ NNP] [NNS ADP NNP] [NNS VBD NNP] [ left 5] [VBD left 5] [ left 5] [ADP left 5] [VERB IN] [ IN] [ VERB IN] [ VERB ] [JJ IN] [VERB IN] [VERB JJ IN] [VERB JJ ] [NOUN IN] [NOUN VERB IN] [NOUN VERB ] [JJ IN NOUN] [VERB IN NOUN] [VERB JJ NOUN] [NOUN IN NOUN] [NOUN VERB NOUN] [ left 5] [VERB left 5] [ left 5] [IN left 5] [ VBD ADP] [VBD ADJ ADP] [NNS VBD ADP] [VBD ADJ ADP NNP] [NNS VBD ADP NNP] [ VBD left 5] [ ADP left 5] [ left 5] [VBD ADP left 5] [ VERB IN] [VERB JJ IN] [NOUN VERB IN] [VERB JJ IN NOUN] [NOUN VERB IN NOUN] [ VERB left 5] [ IN left 5] [ left 5] [VERB IN left 5] [VBD ADP left 5] [ ADP left 5] [ VBD ADP left 5] [ VBD left 5] [ADJ ADP left 5] [VBD ADP left 5] [VBD ADJ ADP left 5] [VBD ADJ left 5] [NNS ADP left 5] [NNS VBD ADP left 5] [NNS VBD left 5] [ADJ ADP NNP left 5] [VBD ADP NNP left 5] [VBD ADJ NNP left 5] [NNS ADP NNP left 5] [NNS VBD NNP left 5] [VERB IN left 5] [ IN left 5] [ VERB IN left 5] [ VERB left 5] [JJ IN left 5] [VERB IN left 5] [VERB JJ IN left 5] [VERB JJ left 5] [NOUN IN left 5] [NOUN VERB IN left 5]
17 Arc Length By Part-of-Speech NOUN ADP DET VERB ADJ counts length
18 Arc Length By Part-of-Speech NOUN ADP DET VERB ADJ counts length
19 Arc Length By Part-of-Speech NOUN ADP DET VERB ADJ counts length
20 bill The to the intends to RTC restrict only borrowings Treasury the unless authorization congressional specific Arc Length Examples The bill intends to restrict the RTC to Treasury borrowings only unless the agency receives specific congressional authorization. receives agency.
21 This was in system financing the new created in law to order the keep from bailout the spending. swelling deficit budget Arc Length Examples This financing system was created in the new law in order to keep the bailout spending from swelling the budget deficit.
22 Arc Length Examples But the RTC also requires working capital to maintain the bad assets of thrifts that are sold until the assets can be sold separately. But the RTC also requires working capital to maintain the bad assets of thrifts that are sold until the assets can be sold separately.
23 Arc Length Examples It s a problem that clearly has to be resolved said David Cooke executive director of the RTC. It s a problem that clearly has to be resolved said David Cooke executive director of the RTC.
24 Arc Length Examples We would have to wait until we have collected on those assets before we can move forward he said. We would have to wait until we have collected on those assets before we can move forward he said.
25 The in the huge language law new complicated has the. fight muddied Arc Length Examples The complicated language in the huge new law has muddied the fight.
26 Arc Length Examples That secrecy leads to a proposal like the one from Ways and Means which seems to me sort of draconian he said. That secrecy leads to a proposal like the one from Ways and Means which seems to me sort of draconian he said.
27 Arc Length Examples The RTC is going to have to pay a price of prior consultation on the Hill if they want that kind of flexibility. The RTC is going to have to pay a price of prior consultation on the Hill if they want that kind of flexibility.
28 Arc Length Heat Map
29 Arc Length Heat Map
30 Banded Matrix
31 Banded Matrix
32 Outer Arc
33 Outer Arc
34 Outer Arc
35 Outer Arc
36 vine Coarse-to-Fine
37 Coarse-to-Fine vine first
38 Coarse-to-Fine cgwire vine first second
39 dynamic programs for parsing
40 Inference Questions questions: How do we reduce inference time to O(n)? How do we decide which arcs to prune? Vine Parsing (Eisner and Smith 2005)
41 Eisner First-Order Rules + h m h r r + 1 m + h e h m m e
42 First-Order Parsing
43 First-Order Parsing
44 First-Order Parsing
45 First-Order Parsing
46 First-Order Parsing
47 First-Order Parsing
48 First-Order Parsing
49 First-Order Parsing
50 First-Order Parsing
51 Vine Parsing Rules + 0 e 0 e 1 e 1 e + 0 e 0 m m e 0 e 0 e + 0 e 0 m m e + 0 e 0 e 1 e 1 e
52 Vine Parsing
53 Vine Parsing
54 Vine Parsing
55 Vine Parsing
56 Vine Parsing
57 Vine Parsing
58 Vine Parsing
59 Vine Parsing
60 Vine Parsing
61 Vine Parsing
62 Vine Parsing
63 Vine Parsing
64 Arc Pruning Prune arcs based on max-marginals. maxmarginal(a) = max (y w) y:a y Can compute using inside-outside algorithm. Generic algorithm using hypergraph parsing.
65 Max-Marginals for First-Order Arcs maxmarginal( ) > threshold?
66 Max-Marginals for Outer Arcs maxmarginal(left ) > threshold?
67 pruning and training
68 Max-Marginal Pruning goal: Define a threshold on max-marginal score. Validation parameter α trades off between speed and accuracy. t α (w) = α max (y w) + (1 α) 1 y A maxmarginal(a w) a A Highest scoring parse upper bounds any max-marginal. sume average of max-marginals is lower than gold.
69 Pruning Threshold feature two w feature one
70 Pruning Threshold max feature two w feature one
71 Pruning Threshold max feature two w feature one
72 Pruning Threshold max feature two w feature one
73 Pruning Threshold max feature two w feature one
74 Pruning Threshold max feature two average max-marginal w feature one
75 Pruning Threshold max feature two average max-marginal w feature one
76 Pruning Threshold max feature two average max-marginal w feature one
77 Pruning Threshold max feature two average max-marginal w feature one
78 Pruning Threshold max feature two α average max-marginal w feature one
79 Pruning Threshold max feature two average max-marginal w feature one
80 Structured Cascade Training (Weiss and Taskar 2011) Train a linear model with a loss function for pruning. Regularized risk minimization with loss based on threshold min w λ w P P [1 y (p) w + t α (p) (w)] + p=1 Can use a simple variant of perceptron/pegasos to train.
81 Structured Cascade Training max feature two w feature one gold
82 Structured Cascade Training max feature two average max-marginal w feature one gold
83 Structured Cascade Training max feature two average max-marginal w feature one gold
84 Structured Cascade Training max feature two average max-marginal w feature one gold
85 Structured Cascade Training max feature two average max-marginal w feature one gold
86 Structured Cascade Training max feature two average max-marginal w feature one gold
87 Structured Cascade Training max feature two average max-marginal w feature one gold
88 Structured Cascade Training feature two w feature one gold
89 Structured Cascade Training feature two max w feature one gold
90 Structured Cascade Training feature two max w feature one gold
91 Structured Cascade Training feature two max w feature one gold
92 experiments
93 Implementation Inference Experiments use a highly-optimized C++ implementation. Baseline first-order parser processes 2000 tokens/sec. Hypergraph parsing framework with shared inference. Model Final models trained with hamming-loss MIRA. Full collection of dependency parsing features (Koo 2010). First- second- and third-order models match state-of-the-art.
94 Baselines NoPrune exhaustive parsing model with no pruning LocalShort unstructured classifier over O(n) short arcs (Bergsma and Cherry 2010) Local unstructured classifier over O(n 2 ) arcs (Bergsma and Cherry 2010) FirstOnly structured first-order model in cascade (Koo 2010) VinePosterior posterior pruning cascade trained with L-BFGS ZhangNivre reimplementation of state-of-the-art k-best transition-based parser (Zhang and Nivre 2011).
95 Speed/Accuracy Experiments: First-Order Parsing NoPrune Local FirstOnly VinePosterior VineCascade ZhangNivre(8) Relative Speed Accuracy
96 Speed/Accuracy Experiments: Second-Order Parsing NoPrune Local FirstOnly VinePosterior VineCascade ZhangNivre(16) Relative Speed Accuracy
97 Speed/Accuracy Experiments: Third-Order Parsing NoPrune Local FirstOnly VinePosterior VineCascade ZhangNivre(64) Relative Speed Accuracy
98 Empirical Complexity: First-Order Parsing NoPrune [2.8] VineCascade [1.4] time sentence length
99 Empirical Complexity: Second-Order Parsing NoPrune [2.8] VineCascade [1.8] time sentence length
100 Empirical Complexity: Third-Order Parsing NoPrune [3.8] VineCascade [1.9] time sentence length
101 Multilingual Experiments: First-Order Parsing En Bg De Pt Sw Zh NoPrune VineCascade Relative Speed
102 Multilingual Experiments: Second-Order Parsing En Bg De Pt Sw Zh NoPrune VineCascade Relative Speed
103 Multilingual Experiments: Third-Order Parsing En Bg De Pt Sw Zh NoPrune VineCascade Relative Speed
104 Special thanks to: Ryan McDonald Hao Zhang Michael Ringgaard Terry Koo Keith Hall Kuzman Ganchev Yoav Goldberg Andre Martins and the rest of the Google NLP team
Dependency 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 informationStructured Prediction Models via the Matrix-Tree Theorem
Structured Prediction Models via the Matrix-Tree Theorem Terry Koo Amir Globerson Xavier Carreras Michael Collins maestro@csail.mit.edu gamir@csail.mit.edu carreras@csail.mit.edu mcollins@csail.mit.edu
More informationAdvanced Graph-Based Parsing Techniques
Advanced Graph-Based Parsing Techniques Joakim Nivre Uppsala University Linguistics and Philology Based on previous tutorials with Ryan McDonald Advanced Graph-Based Parsing Techniques 1(33) Introduction
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 informationNLP Programming Tutorial 11 - The Structured Perceptron
NLP Programming Tutorial 11 - The Structured Perceptron Graham Neubig Nara Institute of Science and Technology (NAIST) 1 Prediction Problems Given x, A book review Oh, man I love this book! This book is
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 informationTransition-based Dependency Parsing with Selectional Branching
Transitionbased Dependency Parsing with Selectional Branching Presented at the 4th workshop on Statistical Parsing in Morphologically Rich Languages October 18th, 2013 Jinho D. Choi University of Massachusetts
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 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 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 informationPersonal Project: Shift-Reduce Dependency Parsing
Personal Project: Shift-Reduce Dependency Parsing 1 Problem Statement The goal of this project is to implement a shift-reduce dependency parser. This entails two subgoals: Inference: We must have a shift-reduce
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 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 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 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 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 informationLog-Linear Models with Structured Outputs
Log-Linear Models with Structured Outputs Natural Language Processing CS 4120/6120 Spring 2016 Northeastern University David Smith (some slides from Andrew McCallum) Overview Sequence labeling task (cf.
More informationPosterior vs. Parameter Sparsity in Latent Variable Models Supplementary Material
Posterior vs. Parameter Sparsity in Latent Variable Models Supplementary Material João V. Graça L 2 F INESC-ID Lisboa, Portugal Kuzman Ganchev Ben Taskar University of Pennsylvania Philadelphia, PA, USA
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 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 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 informationDynamic-oracle Transition-based Parsing with Calibrated Probabilistic Output
Dynamic-oracle Transition-based Parsing with Calibrated Probabilistic Output Yoav Goldberg Computer Science Department Bar Ilan University Ramat Gan, Israel yoav.goldberg@gmail.com Abstract We adapt the
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 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 informationProbabilistic Context Free Grammars. Many slides from Michael Collins
Probabilistic Context Free Grammars Many slides from Michael Collins Overview I Probabilistic Context-Free Grammars (PCFGs) I The CKY Algorithm for parsing with PCFGs A Probabilistic Context-Free Grammar
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 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 informationTransition-based Dependency Parsing with Selectional Branching
Transition-based Dependency Parsing with Selectional Branching Jinho D. Choi Department of Computer Science University of Massachusetts Amherst Amherst, MA, 01003, USA jdchoi@cs.umass.edu Andrew McCallum
More informationIntroduction to Data-Driven Dependency Parsing
Introduction to Data-Driven Dependency Parsing Introductory Course, ESSLLI 2007 Ryan McDonald 1 Joakim Nivre 2 1 Google Inc., New York, USA E-mail: ryanmcd@google.com 2 Uppsala University and Växjö University,
More informationBoosting Ensembles of Structured Prediction Rules
Boosting Ensembles of Structured Prediction Rules Corinna Cortes Google Research 76 Ninth Avenue New York, NY 10011 corinna@google.com Vitaly Kuznetsov Courant Institute 251 Mercer Street New York, NY
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 informationStatistical methods in NLP, lecture 7 Tagging and parsing
Statistical methods in NLP, lecture 7 Tagging and parsing Richard Johansson February 25, 2014 overview of today's lecture HMM tagging recap assignment 3 PCFG recap dependency parsing VG assignment 1 overview
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 informationCS395T: Structured Models for NLP Lecture 19: Advanced NNs I
CS395T: Structured Models for NLP Lecture 19: Advanced NNs I Greg Durrett Administrivia Kyunghyun Cho (NYU) talk Friday 11am GDC 6.302 Project 3 due today! Final project out today! Proposal due in 1 week
More informationParsing with Context-Free Grammars
Parsing with Context-Free Grammars CS 585, Fall 2017 Introduction to Natural Language Processing http://people.cs.umass.edu/~brenocon/inlp2017 Brendan O Connor College of Information and Computer Sciences
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 informationWord Embeddings in Feedforward Networks; Tagging and Dependency Parsing using Feedforward Networks. Michael Collins, Columbia University
Word Embeddings in Feedforward Networks; Tagging and Dependency Parsing using Feedforward Networks Michael Collins, Columbia University Overview Introduction Multi-layer feedforward networks Representing
More informationCS395T: Structured Models for NLP Lecture 19: Advanced NNs I. Greg Durrett
CS395T: Structured Models for NLP Lecture 19: Advanced NNs I Greg Durrett Administrivia Kyunghyun Cho (NYU) talk Friday 11am GDC 6.302 Project 3 due today! Final project out today! Proposal due in 1 week
More informationLecture 9: Hidden Markov Model
Lecture 9: Hidden Markov Model Kai-Wei Chang CS @ University of Virginia kw@kwchang.net Couse webpage: http://kwchang.net/teaching/nlp16 CS6501 Natural Language Processing 1 This lecture v Hidden Markov
More informationHierarchical Low-Rank Tensors for Multilingual Transfer Parsing
Hierarchical Low-Rank Tensors for Multilingual Transfer Parsing Yuan Zhang CSAIL, MIT yuanzh@csail.mit.edu Regina Barzilay CSAIL, MIT regina@csail.mit.edu Abstract Accurate multilingual transfer parsing
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 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 informationSequence Labeling: HMMs & Structured Perceptron
Sequence Labeling: HMMs & Structured Perceptron CMSC 723 / LING 723 / INST 725 MARINE CARPUAT marine@cs.umd.edu HMM: Formal Specification Q: a finite set of N states Q = {q 0, q 1, q 2, q 3, } N N Transition
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 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 informationCS838-1 Advanced NLP: Hidden Markov Models
CS838-1 Advanced NLP: Hidden Markov Models Xiaojin Zhu 2007 Send comments to jerryzhu@cs.wisc.edu 1 Part of Speech Tagging Tag each word in a sentence with its part-of-speech, e.g., The/AT representative/nn
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 informationStatistical Methods for NLP
Statistical Methods for NLP Information Extraction, Hidden Markov Models Sameer Maskey Week 5, Oct 3, 2012 *many slides provided by Bhuvana Ramabhadran, Stanley Chen, Michael Picheny Speech Recognition
More informationProbabilistic Context-Free Grammars. Michael Collins, Columbia University
Probabilistic Context-Free Grammars Michael Collins, Columbia University Overview Probabilistic Context-Free Grammars (PCFGs) The CKY Algorithm for parsing with PCFGs A Probabilistic Context-Free Grammar
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 informationDiscrimina)ve Latent Variable Models. SPFLODD November 15, 2011
Discrimina)ve Latent Variable Models SPFLODD November 15, 2011 Lecture Plan 1. Latent variables in genera)ve models (review) 2. Latent variables in condi)onal models 3. Latent variables in structural SVMs
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 informationWHITE PAPER BENEFITS OF USING EXPERT FX RISK MANAGEMENT RESOURCES PREPARED BY ANDRE CILLIERS DIRECTOR AND CURRENCY RISK STRATEGIST AT TREASURYONE
WHITE PAPER BENEFITS OF USING EXPERT FX RISK MANAGEMENT RESOURCES EXCHANGE RATE RISK MANAGEMENT PREPARED BY ANDRE CILLIERS DIRECTOR AND CURRENCY RISK STRATEGIST AT TREASURYONE SEPTEMBER 2018 Introduction
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 26 February 2018 Recap: tagging POS tagging is a sequence labelling task.
More informationDependency grammar. Recurrent neural networks. Transition-based neural parsing. Word representations. Informs Models
Dependency grammar Morphology Word order Transition-based neural parsing Word representations Recurrent neural networks Informs Models Dependency grammar Morphology Word order Transition-based neural parsing
More informationCKY & Earley Parsing. Ling 571 Deep Processing Techniques for NLP January 13, 2016
CKY & Earley Parsing Ling 571 Deep Processing Techniques for NLP January 13, 2016 No Class Monday: Martin Luther King Jr. Day CKY Parsing: Finish the parse Recognizer à Parser Roadmap Earley parsing Motivation:
More informationSequential Data Modeling - The Structured Perceptron
Sequential Data Modeling - The Structured Perceptron Graham Neubig Nara Institute of Science and Technology (NAIST) 1 Prediction Problems Given x, predict y 2 Prediction Problems Given x, A book review
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 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 informationDistributed Training Strategies for the Structured Perceptron
Distributed Training Strategies for the Structured Perceptron Ryan McDonald Keith Hall Gideon Mann Google, Inc., New York / Zurich {ryanmcd kbhall gmann}@google.com Abstract Perceptron training is widely
More informationMachine Learning for NLP
Machine Learning for NLP Uppsala University Department of Linguistics and Philology Slides borrowed from Ryan McDonald, Google Research Machine Learning for NLP 1(50) Introduction Linear Classifiers Classifiers
More informationNatural Language Processing
Natural Language Processing Global linear models Based on slides from Michael Collins Globally-normalized models Why do we decompose to a sequence of decisions? Can we directly estimate the probability
More informationPolyhedral Outer Approximations with Application to Natural Language Parsing
Polyhedral Outer Approximations with Application to Natural Language Parsing André F. T. Martins 1,2 Noah A. Smith 1 Eric P. Xing 1 1 Language Technologies Institute School of Computer Science Carnegie
More informationStructured Prediction Theory and Algorithms
Structured Prediction Theory and Algorithms Joint work with Corinna Cortes (Google Research) Vitaly Kuznetsov (Google Research) Scott Yang (Courant Institute) MEHRYAR MOHRI MOHRI@ COURANT INSTITUTE & GOOGLE
More informationCS388: Natural Language Processing Lecture 4: Sequence Models I
CS388: Natural Language Processing Lecture 4: Sequence Models I Greg Durrett Mini 1 due today Administrivia Project 1 out today, due September 27 Viterbi algorithm, CRF NER system, extension Extension
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 informationA Context-Free Grammar
Statistical Parsing A Context-Free Grammar S VP VP Vi VP Vt VP VP PP DT NN PP PP P Vi sleeps Vt saw NN man NN dog NN telescope DT the IN with IN in Ambiguity A sentence of reasonable length can easily
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 informationPosterior Sparsity in Unsupervised Dependency Parsing
Journal of Machine Learning Research 10 (2010)?? Submitted??; Published?? Posterior Sparsity in Unsupervised Dependency Parsing Jennifer Gillenwater Kuzman Ganchev João Graça Computer and Information Science
More informationThe Structured Weighted Violations Perceptron Algorithm
The Structured Weighted Violations Perceptron Algorithm Rotem Dror and Roi Reichart Faculty of Industrial Engineering and Management, Technion, IIT {rtmdrr@campus roiri@ie}.technion.ac.il Abstract We present
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 informationACS Introduction to NLP Lecture 3: Language Modelling and Smoothing
ACS Introduction to NLP Lecture 3: Language Modelling and Smoothing Stephen Clark Natural Language and Information Processing (NLIP) Group sc609@cam.ac.uk Language Modelling 2 A language model is a probability
More informationExtracting Information from Text
Extracting Information from Text Research Seminar Statistical Natural Language Processing Angela Bohn, Mathias Frey, November 25, 2010 Main goals Extract structured data from unstructured text Training
More informationMaxent Models and Discriminative Estimation
Maxent Models and Discriminative Estimation Generative vs. Discriminative models (Reading: J+M Ch6) Introduction So far we ve looked at generative models Language models, Naive Bayes But there is now much
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 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 informationMachine Learning for NLP
Machine Learning for NLP Linear Models Joakim Nivre Uppsala University Department of Linguistics and Philology Slides adapted from Ryan McDonald, Google Research Machine Learning for NLP 1(26) Outline
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 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 informationAdaptive Multi-Compositionality for Recursive Neural Models with Applications to Sentiment Analysis. July 31, 2014
Adaptive Multi-Compositionality for Recursive Neural Models with Applications to Sentiment Analysis July 31, 2014 Semantic Composition Principle of Compositionality The meaning of a complex expression
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 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 informationConditional Random Field
Introduction Linear-Chain General Specific Implementations Conclusions Corso di Elaborazione del Linguaggio Naturale Pisa, May, 2011 Introduction Linear-Chain General Specific Implementations Conclusions
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 informationCS626: NLP, Speech and the Web. Pushpak Bhattacharyya CSE Dept., IIT Bombay Lecture 14: Parsing Algorithms 30 th August, 2012
CS626: NLP, Speech and the Web Pushpak Bhattacharyya CSE Dept., IIT Bombay Lecture 14: Parsing Algorithms 30 th August, 2012 Parsing Problem Semantics Part of Speech Tagging NLP Trinity Morph Analysis
More informationA Support Vector Method for Multivariate Performance Measures
A Support Vector Method for Multivariate Performance Measures Thorsten Joachims Cornell University Department of Computer Science Thanks to Rich Caruana, Alexandru Niculescu-Mizil, Pierre Dupont, Jérôme
More informationStructured Prediction
Machine Learning Fall 2017 (structured perceptron, HMM, structured SVM) Professor Liang Huang (Chap. 17 of CIML) x x the man bit the dog x the man bit the dog x DT NN VBD DT NN S =+1 =-1 the man bit the
More informationCS460/626 : Natural Language
CS460/626 : Natural Language Processing/Speech, NLP and the Web (Lecture 23, 24 Parsing Algorithms; Parsing in case of Ambiguity; Probabilistic Parsing) Pushpak Bhattacharyya CSE Dept., IIT Bombay 8 th,
More informationRelaxed Marginal Inference and its Application to Dependency Parsing
Relaxed Marginal Inference and its Application to Dependency Parsing Sebastian Riedel David A. Smith Department of Computer Science University of Massachusetts, Amherst {riedel,dasmith}@cs.umass.edu Abstract
More informationVariational Decoding for Statistical Machine Translation
Variational Decoding for Statistical Machine Translation Zhifei Li, Jason Eisner, and Sanjeev Khudanpur Center for Language and Speech Processing Computer Science Department Johns Hopkins University 1
More informationProbabilistic Graphical Models
School of Computer Science Probabilistic Graphical Models Max-margin learning of GM Eric Xing Lecture 28, Apr 28, 2014 b r a c e Reading: 1 Classical Predictive Models Input and output space: Predictive
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 informationHidden Markov Models
CS769 Spring 2010 Advanced Natural Language Processing Hidden Markov Models Lecturer: Xiaojin Zhu jerryzhu@cs.wisc.edu 1 Part-of-Speech Tagging The goal of Part-of-Speech (POS) tagging is to label each
More informationGeneralized Linear Classifiers in NLP
Generalized Linear Classifiers in NLP (or Discriminative Generalized Linear Feature-Based Classifiers) Graduate School of Language Technology, Sweden 2009 Ryan McDonald Google Inc., New York, USA E-mail:
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 7: Sequence Labeling
http://courses.engr.illinois.edu/cs447 Lecture 7: Sequence Labeling Julia Hockenmaier juliahmr@illinois.edu 3324 Siebel Center Recap: Statistical POS tagging with HMMs (J. Hockenmaier) 2 Recap: Statistical
More informationMidterm sample questions
Midterm sample questions CS 585, Brendan O Connor and David Belanger October 12, 2014 1 Topics on the midterm Language concepts Translation issues: word order, multiword translations Human evaluation Parts
More informationEmpirical Methods in Natural Language Processing Lecture 11 Part-of-speech tagging and HMMs
Empirical Methods in Natural Language Processing Lecture 11 Part-of-speech tagging and HMMs (based on slides by Sharon Goldwater and Philipp Koehn) 21 February 2018 Nathan Schneider ENLP Lecture 11 21
More informationFourth-Order Dependency Parsing
Fourth-Order Dependency Parsing X uezhe Ma 1,2 Hai Zhao 1,2 (1) Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering, Shanghai Jiao Tong University (2)
More information