Analysing Soft Syntax Features and Heuristics for Hierarchical Phrase Based Machine Translation
|
|
- Ada Andrews
- 6 years ago
- Views:
Transcription
1 Analysing Soft Syntax Features and Heuristics for Hierarchical Phrase Based Machine Translation David Vilar, Daniel Stein, Hermann Ney IWSLT 2008, Honolulu, Hawaii 20. October 2008 Human Language Technology and Pattern Recognition Lehrstuhl für Informatik 6 Computer Science Department RWTH Aachen University, Germany D. Vilar, D. Stein, H. Ney Soft-syntax 1 IWSLT October 2008
2 1 Introduction Hierarchical phrase-based models: Generalization of phrase-based-models Allow for gaps in the phrases Integration of reordering in the translation model Study the effect of extraction heuristics Extension with inclusion of (soft) syntactic features D. Vilar, D. Stein, H. Ney Soft-syntax 2 IWSLT October 2008
3 Outline 1 Introduction 2 Hierarchical Phrases 3 Heuristic Features 4 Syntactical Features 5 Experimental Results 6 Conclusions D. Vilar, D. Stein, H. Ney Soft-syntax 3 IWSLT October 2008
4 2 Hierarchical Phrases Formalization as a synchronous CFG Rules of the form X γ, α,, where: X is a non-terminal γ and α are strings of terminals and non-terminals is a one-to-one correspondence between the non-terminals of α and γ Example: X 中 X 0 那个 X 1, It s the X 1 in the X 0 X 也要 X 0 一些 X 1, like to X 0 some X 1 too Additionally: Glue rules S S 0 X 1, S 0 X 1 S X 0, X 0 D. Vilar, D. Stein, H. Ney Soft-syntax 4 IWSLT October 2008
5 Illustration meal toddler a order you did bambini per piatto un ordinato ha Alignment D. Vilar, D. Stein, H. Ney Soft-syntax 5 IWSLT October 2008
6 Illustration meal toddler a order you did bambini per piatto un ordinato ha Standard phrases D. Vilar, D. Stein, H. Ney Soft-syntax 5 IWSLT October 2008
7 Illustration X~1 toddler a X~0 X~0 Example rule bambini per X~1 un D. Vilar, D. Stein, H. Ney Soft-syntax 5 IWSLT October 2008
8 3 Heuristic Features Following features were tested: Paste rule Binary feature for rules of the form X X 0 α, X 0 β or X αx 0, βx 0 Hierarchical penalty Binary feature for hierarchical rules Number of non-terminals Two binary features indicating if the rule has one or two non-terminals. Extended glue rule added rule of the form X X 0 X 1, X 0 X 1 D. Vilar, D. Stein, H. Ney Soft-syntax 6 IWSLT October 2008
9 4 Syntactical Features Goal: include linguistic information from a deep syntactic parser Idea: introduce additional soft syntactic features This can be done during the extraction of the phrases No additional computational costs during decoding Can be done both on source and target side Rules are not filtered out D. Vilar, D. Stein, H. Ney Soft-syntax 7 IWSLT October 2008
10 Valid syntactical phrases A phrase is valid when a node exists that completely covers all positions In order to obtain a normalized score, we add up all the counts and divide by the number of occurences of the phrase pair S S WHADVP VP VP WRB AUX NP VV P NP Where is DT the JJ public NN toilet 洗手间 PP 在 PN 哪里 Extracted rule: X 0 在哪里 # Where is X 0 D. Vilar, D. Stein, H. Ney Soft-syntax 8 IWSLT October 2008
11 Scoring variants m(i, j) = minimum number of words to be deleted or added to a phrase, so that it fits the yield of a node S WHADVP VP WRB AUX NP Where is DT JJ NN Source Phrases: the public toilet public toilet is the D. Vilar, D. Stein, H. Ney Soft-syntax 9 IWSLT October 2008
12 Scoring variants m(i, j) = minimum number of words to be deleted or added to a phrase, so that it fits the yield of a node S WHADVP VP WRB AUX NP Where is DT JJ NN Source Phrases: the public toilet public toilet m(i, j) = 1 is the D. Vilar, D. Stein, H. Ney Soft-syntax 9 IWSLT October 2008
13 Scoring variants m(i, j) = minimum number of words to be deleted or added to a phrase, so that it fits the yield of a node S WHADVP VP WRB AUX NP Where is DT JJ NN Source Phrases: the public toilet public toilet m(i, j) = 1 is the m(i, j) = 1 D. Vilar, D. Stein, H. Ney Soft-syntax 9 IWSLT October 2008
14 Four count ( smoothing ) variants: δ (m(i, j), 0) binary c(i, j t) := 1 m(i, j) exp (m(i, j)) j i (j i) + m(i, j) linear exponentional relative D. Vilar, D. Stein, H. Ney Soft-syntax 10 IWSLT October 2008
15 5 Experimental Results IWSLT BTEC Data (Tourist and Travel domain) Chinese English Training data Sentences Running words Vocabulary Test 2004 Data Sentences 500 Running words OOVs Test 2005 Data Sentences 506 Running words OOVs Test 2008 Data Sentences 507 Running words 6325 OOVs 87 D. Vilar, D. Stein, H. Ney Soft-syntax 11 IWSLT October 2008
16 Results test04 test05 test08 BLEU TER BLEU TER BLEU baseline non-syntactic information hierarch paste glue NT2NT syntactic information binary linear exponential relative D. Vilar, D. Stein, H. Ney Soft-syntax 12 IWSLT October 2008
17 Results test04 test05 test08 BLEU TER BLEU TER BLEU baseline non-syntactic information hierarch + paste hierarch + paste + glue hierarch + paste + glue2 + 1NT2NT combination of both syntactic and non-syntactic information (all features) binary linear exponential relative D. Vilar, D. Stein, H. Ney Soft-syntax 13 IWSLT October 2008
18 Example Translations reference Where is the exchange counter? baseline The currency exchange office is syntactical Where is the currency exchange office? reference Could you exchange it for a new one? baseline You can buy a new one? syntactical Could you change it for a new one? reference You can take our airport shuttle bus to pick up the car. baseline You can take our airport shuttle bus with me. syntactical You can take our the airport shuttle bus come to pick it up. D. Vilar, D. Stein, H. Ney Soft-syntax 14 IWSLT October 2008
19 6 Conclusions Analyzed heuristics for phrase extraction Introduced soft syntactic constraints Use of source- and target-side information No additional search effort High variability of results Test on bigger corpora Bigger improvements when dealing with speech input (system talk tomorrow!) Applicable also to phrase-based systems D. Vilar, D. Stein, H. Ney Soft-syntax 15 IWSLT October 2008
20 Analysing Soft Syntax Features and Heuristics for Hierarchical Phrase Based Machine Translation David Vilar, Daniel Stein, Hermann Ney IWSLT 2008, Honolulu, Hawaii 20. October 2008 Human Language Technology and Pattern Recognition Lehrstuhl für Informatik 6 Computer Science Department RWTH Aachen University, Germany D. Vilar, D. Stein, H. Ney Soft-syntax 16 IWSLT October 2008
21 The Blackslide GoBack
Triplet Lexicon Models for Statistical Machine Translation
Triplet Lexicon Models for Statistical Machine Translation Saša Hasan, Juri Ganitkevitch, Hermann Ney and Jesús Andrés Ferrer lastname@cs.rwth-aachen.de CLSP Student Seminar February 6, 2009 Human Language
More informationA Syntax-based Statistical Machine Translation Model. Alexander Friedl, Georg Teichtmeister
A Syntax-based Statistical Machine Translation Model Alexander Friedl, Georg Teichtmeister 4.12.2006 Introduction The model Experiment Conclusion Statistical Translation Model (STM): - mathematical model
More informationNeural Hidden Markov Model for Machine Translation
Neural Hidden Markov Model for Machine Translation Weiyue Wang, Derui Zhu, Tamer Alkhouli, Zixuan Gan and Hermann Ney {surname}@i6.informatik.rwth-aachen.de July 17th, 2018 Human Language Technology and
More informationTALP Phrase-Based System and TALP System Combination for the IWSLT 2006 IWSLT 2006, Kyoto
TALP Phrase-Based System and TALP System Combination for the IWSLT 2006 IWSLT 2006, Kyoto Marta R. Costa-jussà, Josep M. Crego, Adrià de Gispert, Patrik Lambert, Maxim Khalilov, José A.R. Fonollosa, José
More informationPhrase-Based Statistical Machine Translation with Pivot Languages
Phrase-Based Statistical Machine Translation with Pivot Languages N. Bertoldi, M. Barbaiani, M. Federico, R. Cattoni FBK, Trento - Italy Rovira i Virgili University, Tarragona - Spain October 21st, 2008
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 informationThis kind of reordering is beyond the power of finite transducers, but a synchronous CFG can do this.
Chapter 12 Synchronous CFGs Synchronous context-free grammars are a generalization of CFGs that generate pairs of related strings instead of single strings. They are useful in many situations where one
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 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 informationNational Centre for Language Technology School of Computing Dublin City University
with with National Centre for Language Technology School of Computing Dublin City University Parallel treebanks A parallel treebank comprises: sentence pairs parsed word-aligned tree-aligned (Volk & Samuelsson,
More informationImproved Decipherment of Homophonic Ciphers
Improved Decipherment of Homophonic Ciphers Malte Nuhn and Julian Schamper and Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department, RWTH Aachen University, Aachen,
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 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 informationA Probabilistic Forest-to-String Model for Language Generation from Typed Lambda Calculus Expressions
A Probabilistic Forest-to-String Model for Language Generation from Typed Lambda Calculus Expressions Wei Lu and Hwee Tou Ng National University of Singapore 1/26 The Task (Logical Form) λx 0.state(x 0
More informationFast and Scalable Decoding with Language Model Look-Ahead for Phrase-based Statistical Machine Translation
Fast and Scalable Decoding with Language Model Look-Ahead for Phrase-based Statistical Machine Translation Joern Wuebker, Hermann Ney Human Language Technology and Pattern Recognition Group 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 informationAspects of Tree-Based Statistical Machine Translation
Aspects of Tree-Based tatistical Machine Translation Marcello Federico (based on slides by Gabriele Musillo) Human Language Technology FBK-irst 2011 Outline Tree-based translation models: ynchronous context
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 informationThe Geometry of Statistical Machine Translation
The Geometry of Statistical Machine Translation Presented by Rory Waite 16th of December 2015 ntroduction Linear Models Convex Geometry The Minkowski Sum Projected MERT Conclusions ntroduction We provide
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 informationRandom Generation of Nondeterministic Tree Automata
Random Generation of Nondeterministic Tree Automata Thomas Hanneforth 1 and Andreas Maletti 2 and Daniel Quernheim 2 1 Department of Linguistics University of Potsdam, Germany 2 Institute for Natural Language
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 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 informationDT2118 Speech and Speaker Recognition
DT2118 Speech and Speaker Recognition Language Modelling Giampiero Salvi KTH/CSC/TMH giampi@kth.se VT 2015 1 / 56 Outline Introduction Formal Language Theory Stochastic Language Models (SLM) N-gram Language
More informationOverview (Fall 2007) Machine Translation Part III. Roadmap for the Next Few Lectures. Phrase-Based Models. Learning phrases from alignments
Overview Learning phrases from alignments 6.864 (Fall 2007) Machine Translation Part III A phrase-based model Decoding in phrase-based models (Thanks to Philipp Koehn for giving me slides from his EACL
More informationLanguage Model Rest Costs and Space-Efficient Storage
Language Model Rest Costs and Space-Efficient Storage Kenneth Heafield Philipp Koehn Alon Lavie Carnegie Mellon, University of Edinburgh July 14, 2012 Complaint About Language Models Make Search Expensive
More informationSpeech Translation: from Singlebest to N-Best to Lattice Translation. Spoken Language Communication Laboratories
Speech Translation: from Singlebest to N-Best to Lattice Translation Ruiqiang ZHANG Genichiro KIKUI Spoken Language Communication Laboratories 2 Speech Translation Structure Single-best only ASR Single-best
More informationMultiple System Combination. Jinhua Du CNGL July 23, 2008
Multiple System Combination Jinhua Du CNGL July 23, 2008 Outline Introduction Motivation Current Achievements Combination Strategies Key Techniques System Combination Framework in IA Large-Scale Experiments
More informationLecture 7: Introduction to syntax-based MT
Lecture 7: Introduction to syntax-based MT Andreas Maletti Statistical Machine Translation Stuttgart December 16, 2011 SMT VII A. Maletti 1 Lecture 7 Goals Overview Tree substitution grammars (tree automata)
More informationSyntax-based Statistical Machine Translation
Syntax-based Statistical Machine Translation Philip Williams and Philipp Koehn 29 October 2014 Part I Part II - Introduction - Rule Extraction Part III - Decoding Part IV - Extensions Syntax-based Statistical
More informationGeneralized Stack Decoding Algorithms for Statistical Machine Translation
Generalized Stack Decoding Algorithms for Statistical Machine Translation Daniel Ortiz Martínez Inst. Tecnológico de Informática Univ. Politécnica de Valencia 4607 Valencia, Spain dortiz@iti.upv.es Ismael
More informationA DOP Model for LFG. Rens Bod and Ronald Kaplan. Kathrin Spreyer Data-Oriented Parsing, 14 June 2005
A DOP Model for LFG Rens Bod and Ronald Kaplan Kathrin Spreyer Data-Oriented Parsing, 14 June 2005 Lexical-Functional Grammar (LFG) Levels of linguistic knowledge represented formally differently (non-monostratal):
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 informationUniversität Potsdam Institut für Informatik Lehrstuhl Maschinelles Lernen. Machine Translation. Uwe Dick
Universität Potsdam Institut für Informatik Lehrstuhl Maschinelles Lernen Machine Translation Uwe Dick Google Translate Rosetta Stone Hieroglyphs Demotic Greek Machine Translation Automatically translate
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 informationIBM Model 1 for Machine Translation
IBM Model 1 for Machine Translation Micha Elsner March 28, 2014 2 Machine translation A key area of computational linguistics Bar-Hillel points out that human-like translation requires understanding of
More informationSYNTHER A NEW M-GRAM POS TAGGER
SYNTHER A NEW M-GRAM POS TAGGER David Sündermann and Hermann Ney RWTH Aachen University of Technology, Computer Science Department Ahornstr. 55, 52056 Aachen, Germany {suendermann,ney}@cs.rwth-aachen.de
More informationGoogle s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Google s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation Y. Wu, M. Schuster, Z. Chen, Q.V. Le, M. Norouzi, et al. Google arxiv:1609.08144v2 Reviewed by : Bill
More informationPart I - Introduction Part II - Rule Extraction Part III - Decoding Part IV - Extensions
Syntax-based Statistical Machine Translation Philip Williams and Philipp Koehn 29 October 2014 Part I - Introduction Part II - Rule Extraction Part III - Decoding Part IV - Extensions Syntax-based Statistical
More informationExpectation Maximization (EM)
Expectation Maximization (EM) The EM algorithm is used to train models involving latent variables using training data in which the latent variables are not observed (unlabeled data). This is to be contrasted
More informationChapter 14 (Partially) Unsupervised Parsing
Chapter 14 (Partially) Unsupervised Parsing The linguistically-motivated tree transformations we discussed previously are very effective, but when we move to a new language, we may have to come up with
More informationOut of GIZA Efficient Word Alignment Models for SMT
Out of GIZA Efficient Word Alignment Models for SMT Yanjun Ma National Centre for Language Technology School of Computing Dublin City University NCLT Seminar Series March 4, 2009 Y. Ma (DCU) Out of Giza
More informationNatural Language Processing (CSEP 517): Machine Translation
Natural Language Processing (CSEP 57): Machine Translation Noah Smith c 207 University of Washington nasmith@cs.washington.edu May 5, 207 / 59 To-Do List Online quiz: due Sunday (Jurafsky and Martin, 2008,
More informationstatistical machine translation
statistical machine translation P A R T 3 : D E C O D I N G & E V A L U A T I O N CSC401/2511 Natural Language Computing Spring 2019 Lecture 6 Frank Rudzicz and Chloé Pou-Prom 1 University of Toronto Statistical
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 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 informationGappy Phrasal Alignment by Agreement
Gappy Phrasal Alignment by Agreement Mohit Bansal UC Berkeley, CS Division mbansal@cs.berkeley.edu Chris Quirk Microsoft Research chrisq@microsoft.com Robert C. Moore Google Research robert.carter.moore@gmail.com
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 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 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 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 informationCOMS 4705, Fall Machine Translation Part III
COMS 4705, Fall 2011 Machine Translation Part III 1 Roadmap for the Next Few Lectures Lecture 1 (last time): IBM Models 1 and 2 Lecture 2 (today): phrase-based models Lecture 3: Syntax in statistical machine
More informationApplications of Tree Automata Theory Lecture VI: Back to Machine Translation
Applications of Tree Automata Theory Lecture VI: Back to Machine Translation Andreas Maletti Institute of Computer Science Universität Leipzig, Germany on leave from: Institute for Natural Language Processing
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 informationDiscriminative Training. March 4, 2014
Discriminative Training March 4, 2014 Noisy Channels Again p(e) source English Noisy Channels Again p(e) p(g e) source English German Noisy Channels Again p(e) p(g e) source English German decoder e =
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 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 informationIntroduction to Computational Linguistics
Introduction to Computational Linguistics Olga Zamaraeva (2018) Based on Bender (prev. years) University of Washington May 3, 2018 1 / 101 Midterm Project Milestone 2: due Friday Assgnments 4& 5 due dates
More informationFoundations of Informatics: a Bridging Course
Foundations of Informatics: a Bridging Course Week 3: Formal Languages and Semantics Thomas Noll Lehrstuhl für Informatik 2 RWTH Aachen University noll@cs.rwth-aachen.de http://www.b-it-center.de/wob/en/view/class211_id948.html
More informationDecoding Revisited: Easy-Part-First & MERT. February 26, 2015
Decoding Revisited: Easy-Part-First & MERT February 26, 2015 Translating the Easy Part First? the tourism initiative addresses this for the first time the die tm:-0.19,lm:-0.4, d:0, all:-0.65 tourism touristische
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 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 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 informationDiscriminative Training
Discriminative Training February 19, 2013 Noisy Channels Again p(e) source English Noisy Channels Again p(e) p(g e) source English German Noisy Channels Again p(e) p(g e) source English German decoder
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 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 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 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 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 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 informationA Systematic Comparison of Training Criteria for Statistical Machine Translation
A Systematic Comparison of Training Criteria for Statistical Machine Translation Richard Zens and Saša Hasan and Hermann Ney Human Language Technology and Pattern Recognition Lehrstuhl für Informatik 6
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 informationStructure and Complexity of Grammar-Based Machine Translation
Structure and of Grammar-Based Machine Translation University of Padua, Italy New York, June 9th, 2006 1 2 Synchronous context-free grammars Definitions Computational problems 3 problem SCFG projection
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 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 informationProbabilistic Context Free Grammars. Many slides from Michael Collins and Chris Manning
Probabilistic Context Free Grammars Many slides from Michael Collins and Chris Manning Overview I Probabilistic Context-Free Grammars (PCFGs) I The CKY Algorithm for parsing with PCFGs A Probabilistic
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 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 informationFeatures of Statistical Parsers
Features of tatistical Parsers Preliminary results Mark Johnson Brown University TTI, October 2003 Joint work with Michael Collins (MIT) upported by NF grants LI 9720368 and II0095940 1 Talk outline tatistical
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 informationProbabilistic Graphical Models: Lagrangian Relaxation Algorithms for Natural Language Processing
Probabilistic Graphical Models: Lagrangian Relaxation Algorithms for atural Language Processing Alexander M. Rush (based on joint work with Michael Collins, Tommi Jaakkola, Terry Koo, David Sontag) Uncertainty
More informationAn Empirical Study on Computing Consensus Translations from Multiple Machine Translation Systems
An Empirical Study on Computing Consensus Translations from Multiple Machine Translation Systems Wolfgang Macherey Google Inc. 1600 Amphitheatre Parkway Mountain View, CA 94043, USA wmach@google.com Franz
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 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 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 informationTheory of Alignment Generators and Applications to Statistical Machine Translation
Theory of Alignment Generators and Applications to Statistical Machine Translation Raghavendra Udupa U Hemanta K Mai IBM India Research Laboratory, New Delhi {uraghave, hemantkm}@inibmcom Abstract Viterbi
More informationCoverage Embedding Models for Neural Machine Translation
Coverage Embedding Models for Neural Machine Translation Haitao Mi Baskaran Sankaran Zhiguo Wang Abe Ittycheriah T.J. Watson Research Center IBM 1101 Kitchawan Rd, Yorktown Heights, NY 10598 {hmi, bsankara,
More informationA Discriminative Model for Semantics-to-String Translation
A Discriminative Model for Semantics-to-String Translation Aleš Tamchyna 1 and Chris Quirk 2 and Michel Galley 2 1 Charles University in Prague 2 Microsoft Research July 30, 2015 Tamchyna, Quirk, Galley
More informationDesign and Implementation of Speech Recognition Systems
Design and Implementation of Speech Recognition Systems Spring 2013 Class 7: Templates to HMMs 13 Feb 2013 1 Recap Thus far, we have looked at dynamic programming for string matching, And derived DTW from
More informationLearning to translate with neural networks. Michael Auli
Learning to translate with neural networks Michael Auli 1 Neural networks for text processing Similar words near each other France Spain dog cat Neural networks for text processing Similar words near each
More informationIntroduction to Semantics. The Formalization of Meaning 1
The Formalization of Meaning 1 1. Obtaining a System That Derives Truth Conditions (1) The Goal of Our Enterprise To develop a system that, for every sentence S of English, derives the truth-conditions
More information6.864: Lecture 17 (November 10th, 2005) Machine Translation Part III
6.864: Lecture 17 (November 10th, 2005) Machine Translation Part III Overview A Phrase-Based Model: (Koehn, Och and Marcu 2003) Syntax Based Model 1: (Wu 1995) Syntax Based Model 2: (Yamada and Knight
More informationLecture 25: Cook s Theorem (1997) Steven Skiena. skiena
Lecture 25: Cook s Theorem (1997) Steven Skiena Department of Computer Science State University of New York Stony Brook, NY 11794 4400 http://www.cs.sunysb.edu/ skiena Prove that Hamiltonian Path is NP
More informationarxiv: v1 [cs.cl] 22 Jun 2015
Neural Transformation Machine: A New Architecture for Sequence-to-Sequence Learning arxiv:1506.06442v1 [cs.cl] 22 Jun 2015 Fandong Meng 1 Zhengdong Lu 2 Zhaopeng Tu 2 Hang Li 2 and Qun Liu 1 1 Institute
More informationParsing. Probabilistic CFG (PCFG) Laura Kallmeyer. Winter 2017/18. Heinrich-Heine-Universität Düsseldorf 1 / 22
Parsing Probabilistic CFG (PCFG) Laura Kallmeyer Heinrich-Heine-Universität Düsseldorf Winter 2017/18 1 / 22 Table of contents 1 Introduction 2 PCFG 3 Inside and outside probability 4 Parsing Jurafsky
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 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 informationNatural Language Processing SoSe Language Modelling. (based on the slides of Dr. Saeedeh Momtazi)
Natural Language Processing SoSe 2015 Language Modelling Dr. Mariana Neves April 20th, 2015 (based on the slides of Dr. Saeedeh Momtazi) Outline 2 Motivation Estimation Evaluation Smoothing Outline 3 Motivation
More informationA Tree-Position Kernel for Document Compression
A Tree-Position Kernel for Document Compression Hal Daumé III University of Southern California Department of Computer Science Information Sciences Institute 4676 Admiralty Way, Suite 1001 Marina del Rey,
More informationExam: Synchronous Grammars
Exam: ynchronous Grammars Duration: 3 hours Written documents are allowed. The numbers in front of questions are indicative of hardness or duration. ynchronous grammars consist of pairs of grammars whose
More information