Hierarchical Phrase-Based Translation with WFSTs. Weighted Finite State Transducers
|
|
- Vincent York
- 5 years ago
- Views:
Transcription
1 Hierarchical Phrase-Based Translation with Weighted Finite State Transducers Gonzalo Iglesias 1 Adrià de Gispert 2 Eduardo R. Banga 1 William Byrne 2 1 Department of Signal Processing and Communications University of Vigo, Spain 2 Department of Engineering. University of Cambridge, U.K. NAACL-HLT 2009, Boulder, Colorado university-logo
2 Outline 1 2
3 Outline 1 2
4 I HiFST: New hierarchical decoder that uses lattices (WFSTs) rather than k-best lists Why use Lattices instead of k-best lists? Compactness and Efficiency Semiring Operations rmepsilon,determinize, minimize, compose, prune shortestpath,... WFSTs: OpenFST, available at openfst.org (Allauzen et al. 2007)
5 II classical CYK algorithm: source side, hypotheses recombination, no pruning Given a sentence s 1...s J, find out every derivation starting at cell (S, 1, J) Lattices L(N, x, y) are built for each cell following back-pointers of the grid Objective is lattice L(S, 1, J), at the top of the grid university-logo
6 Outline 1 2
7 I Consider sentence s 1 s 2 s 3 We are looking for L(S, 1, 3) Represents all the translations generated by derivations covering span s 1 s 2 s 3 Toy grammar: R 1 : X s 1 s 2 s 3,t 1 t 2 R 2 : X s 1 s 2,t 7 t 8 R 3 : X s 3,t 9 R 4 : S X,X R 5 : S S X,S X R 6 : X s 1,t 20 R 7 : X X 1 s 2 X 2,X 1 t 10 X 2 R 8 : X X 1 s 2 X 2,X 2 t 10 X 1 university-logo
8 II Phrase-based Scenario R 1 : X s 1 s 2 s 3,t 1 t 2 R 2 : X s 1 s 2,t 7 t 8 R 3 : X s 3,t 9 R 4 : S X,X R 5 : S S X,S X R 2 : R 1 : t7 0 1 t1 0 1 t8 2 R 3 : t2 2 t9 0 1 R 5 : t7 0 1 t8 2 t9 3
9 III Hierarchical Scenario R 3 : X s 3,t 9 R 4 : S X,X R 6 : X s 1,t 20 R 7 : X X 1 s 2 X 2,X 1 t 10 X 2 R 8 : X X 1 s 2 X 2,X 2 t 10 X 1 R 6 : R 7 : t t t10 R 3 : 2 t9 0 1 t9 3 R 8 : t9 0 1 t10 2 t20 3
10 IV Cell Lattice 1 t2 t1 t7 2 t8 3 t9 0 t20 t9 4 t10 5 t9 t t10 7 Rule lattices are merged (i.e. with union) into one single (top) cell lattice university-logo
11 Outline 1 2
12 A cell lattice is a union of rule lattices: L(N, x, y) = L(N, x, y, r) (1) r R(N,x,y) A rule lattice is a concatenation of element lattices: L(N, x, y, r) = L(N, x, y, r, i) (2) i=1.. α r An element lattice may be a simple arc binding two states (terminal,i.e. word) or a sublattice (non-terminal): { A(α L(N, x, y, r, i) = i ) if α i T L(N, x, y ) else (3) university-logo
13 A procedure for lattice translation 1 function buildfst(n,x,y) 2 if L(N, x, y) exists, return L(N, x, y) 3 for each rule applied in cell (N, x, y), 4 for each element in rule 5 if element is a word, create A(element) 6-8 else buildfst(backpointers(element)) 9 Create rule lattice by catenation of element lattices 10 Create cell lattice L(N, x, y) by unioning rule lattices Reduce L(N, x, y) with semiring operations and return
14 Outline 1 2
15 I As the algorithm goes up the grid, lattices grow in complexity Severe memory and speed problems Solution: Delay translation using unique pointers to sublattices skeleton lattices Once the building procedure has finished, i.e. L(S, 1, J) has been built, just expand it... Substituting recursively each special unique pointer by appropriate sublattice
16 II
17 III Easily implemented. Formally, we define g(n, x, y) as the unique pointer for a given cell. Then change Equation??: { L(N, x, y, r, i) = A(α i ) if α i T L(N, x, y ) else into: { L(N, x, y, r, i) = A(α i ) if α i T A(g(N, x, y )) else (4)
18 IV t1 1 t2 g(x,1,1) 3 t10 0 g(x,1,2) g(x,1,1) g(x,3,1) t10 t10 g(x,3,1) 4 6 g(x,3,1) g(x,1,1) 7 0 t1 g(x,3,1) g(x,1,2) 4 1 t10 2 t2 5 g(x,3,1) g(x,1,1) 6 Usual operations (rmepsilon, determinize, minimize, etc) still work! Reduction of lattice size
19 Outline 1 2
20 Final translation lattice L(S, 1, J) typically requires pruning Compose with Language Model of target words Perform likelihood-based pruning (Allauzen et al 2007) in Search: If number of states, non-terminal category and source span meet certain conditions, then: Expand Pointers in translation Lattice and Compose with Language Model Perform likelihood-based pruning of the lattice Remove Language Model
21 Outline 1 2
22 I HCP: Hierarchical Cube decoder, k-best=10000 NIST MT08 Arabic-to-English and Chinese-to-English translation tasks. Hiero Shallow for Arabic (Iglesias et al. 2009) Hiero Full for Chinese MET optimization done in the usual way with n-best lists. Features: target language model translation models,lexical models word and rule penalties, glue rule three rule count features (Bender et al. 2007)
23 II English LM: 4-gram over 965 million word subset English Gigaword Third Edition Rescoring steps: Large-LM rescoring of best list with 5-gram zero cut-off stupid back-off language models (T. Brants et al. 2007) 4.7B words of English nw, vocabulary used based on the phrases covered by the parallel text Implemented with WFSTs (failure transitions) Minimum Bayes Risk (MBR). Rescore 1000-best hyps
24 III AR EN No pruning in search speed increased, HCP search errors: 18% Richer search space: increased gains from 5Gram LM + Minimum Bayes Risk rescoring decoder mt02-05-tune mt02-05-test mt08 BLEU TER BLEU TER BLEU TER a HCP g+MBR b HiFST g+MBR
25 IV ZH EN More efficient search: 48% reduction in search errors HCP improves if using HiFST MET parameters (b) HiFST is comparable to HCP in first pass HiFST produces richer/better hypotheses for rescoring decoder MET tune-nw test-nw mt08 BLEU TER BLEU TER BLEU TER a HCP HCP b HCP HiFST g+MBR c HiFST HiFST g+MBR
26 I We have introduced HiFST, a new hierarchical decoder based on WFSTs Easy to implement, as complexity is hidden by OpenFST library Delayed translation effectively reduces complexity during lattice construction in search is completely avoided for AR EN, yielding a very fast translation ZH EN requires pruning, but it is more selective than HCP (i.e. fired by non-terminal, number of states, span, etc) university-logo
27 II Fewer search errors in the k-best translation hypotheses improves rescoring and MBR MET parameter optimization is improved using HiFST HiFST will be available to download soon
28 Thank you! Questions?
THE CUED NIST 2009 ARABIC-ENGLISH SMT SYSTEM
THE CUED NIST 2009 ARABIC-ENGLISH SMT SYSTEM Adrià de Gispert, Gonzalo Iglesias, Graeme Blackwood, Jamie Brunning, Bill Byrne NIST Open MT 2009 Evaluation Workshop Ottawa, The CUED SMT system Lattice-based
More informationHierarchical Phrase-Based Translation with Weighted Finite State Transducers
Hierarchical Phrase-Based Translation with Weighted Finite State Transducers Gonzalo Iglesias Adrià de Gispert Eduardo R. Banga William Byrne University of Vigo. Dept. of Signal Processing and Communications.
More informationFluency Constraints for Minimum Bayes-Risk Decoding of Statistical Machine Translation Lattices
Fluency Constraints for Minimum Bayes-Risk Decoding of Statistical Machine Translation Lattices Graeme Blackwood and Adrià de Gispert and William Byrne Machine Intelligence Laboratory, Department of Engineering,
More informationLocal Phrase Reordering Models for Statistical Machine Translation
Local Phrase Reordering Models for Statistical Machine Translation Shankar Kumar, William Byrne Center for Language and Speech Processing, Johns Hopkins University, 3400 North Charles Street, Baltimore,
More informationTuning. Philipp Koehn presented by Gaurav Kumar. 28 September 2017
Tuning Philipp Koehn presented by Gaurav Kumar 28 September 2017 The Story so Far: Generative Models 1 The definition of translation probability follows a mathematical derivation argmax e p(e f) = argmax
More informationEfficient Minimum Error Rate Training and Minimum Bayes-Risk Decoding for Translation Hypergraphs and Lattices
Efficient Minimum Error Rate Training and Minimum Bayes-Risk Decoding for Translation Hypergraphs and Lattices Shankar Kumar 1 and Wolfgang Macherey 1 and Chris Dyer 2 and Franz Och 1 1 Google Inc. 1600
More informationWFST-based Grapheme-to-Phoneme Conversion: Open Source Tools for Alignment, Model-Building and Decoding
WFST-based Grapheme-to-Phoneme Conversion: Open Source Tools for Alignment, Model-Building and Decoding Josef R. Novak, Nobuaki Minematsu, Keikichi Hirose Graduate School of Information Science and Technology
More informationWord Graphs for Statistical Machine Translation
Word Graphs for Statistical Machine Translation Richard Zens and Hermann Ney Chair of Computer Science VI RWTH Aachen University {zens,ney}@cs.rwth-aachen.de Abstract Word graphs have various applications
More informationJoint Decoding with Multiple Translation Models
Joint Decoding with Multiple Translation Models Yang Liu, Haitao Mi, Yang Feng, and Qun Liu Institute of Computing Technology, Chinese Academy of ciences {yliu,htmi,fengyang,liuqun}@ict.ac.cn 8/10/2009
More informationLexicographic Semirings for Exact Automata Encoding of Sequence Models
Lexicographic Semirings for Exact Automata Encoding of Sequence Models Brian Roark, Richard Sproat, and Izhak Shafran {roark,rws,zak}@cslu.ogi.edu Abstract In this paper we introduce a novel use of the
More informationA Weighted Finite State Transducer Implementation of the Alignment Template Model for Statistical Machine Translation.
A Weighted Finite State Transducer Implementation of the Alignment Template Model for Statistical Machine Translation May 29, 2003 Shankar Kumar and Bill Byrne Center for Language and Speech Processing
More informationBBN System Description for WMT10 System Combination Task
BBN System Description for WMT10 System Combination Task Antti-Veikko I. Rosti and Bing Zhang and Spyros Matsoukas and Richard Schwartz Raytheon BBN Technologies, 10 Moulton Street, Cambridge, MA 018,
More informationKnowledge-Based Word Lattice Rescoring in a Dynamic Context. Todd Shore, Friedrich Faubel, Hartmut Helmke, Dietrich Klakow
Knowledge-Based Word Lattice Rescoring in a Dynamic Context Todd Shore, Friedrich Faubel, Hartmut Helmke, Dietrich Klakow Section I Motivation Motivation Problem: difficult to incorporate higher-level
More informationOverview. Search and Decoding. HMM Speech Recognition. The Search Problem in ASR (1) Today s lecture. Steve Renals
Overview Search and Decoding Steve Renals Automatic Speech Recognition ASR Lecture 10 January - March 2012 Today s lecture Search in (large vocabulary) speech recognition Viterbi decoding Approximate search
More informationWeighted Finite State Transducers in Automatic Speech Recognition
Weighted Finite State Transducers in Automatic Speech Recognition ZRE lecture 10.04.2013 Mirko Hannemann Slides provided with permission, Daniel Povey some slides from T. Schultz, M. Mohri and M. Riley
More informationBetter Word Alignment with Supervised ITG Models. Aria Haghighi, John Blitzer, John DeNero, and Dan Klein UC Berkeley
Better Word Alignment with Supervised ITG Models Aria Haghighi, John Blitzer, John DeNero, and Dan Klein UC Berkeley Word Alignment s Indonesia parliament court in arraigned speaker Word Alignment s Indonesia
More informationTALP: Xgram-based Spoken Language Translation System Adrià de Gispert José B. Mariño
TALP: Xgram-based Spoken Language Translation System Adrià de Gispert José B. Mariño Outline Overview Outline Translation generation Training IWSLT'04 Chinese-English supplied task results Conclusion and
More informationAutomatic Speech Recognition (ASR)
Automatic Speech Recognition (ASR) February 2018 Reza Yazdani Aminabadi Universitat Politecnica de Catalunya (UPC) State-of-the-art State-of-the-art ASR system: DNN+HMM Speech (words) Sound Signal Graph
More informationExact Decoding of Syntactic Translation Models through Lagrangian Relaxation
Exact Decoding of Syntactic Translation Models through Lagrangian Relaxation Abstract We describe an exact decoding algorithm for syntax-based statistical translation. The approach uses Lagrangian relaxation
More informationParsing Part II. (Ambiguity, Top-down parsing, Left-recursion Removal)
Parsing Part II (Ambiguity, Top-down parsing, Left-recursion Removal) Ambiguous Grammars Definitions If a grammar has more than one leftmost derivation for a single sentential form, the grammar is ambiguous
More informationK-best Parsing Algorithms
K-best Parsing Algorithms Liang Huang University of Pennsylvania joint work with David Chiang (USC Information Sciences Institute) k-best Parsing Liang Huang (Penn) k-best parsing 2 k-best Parsing I saw
More informationModeling Phonetic Context with Non-random Forests for Speech Recognition
Modeling Phonetic Context with Non-random Forests for Speech Recognition Hainan Xu Center for Language and Speech Processing, Johns Hopkins University September 4, 2015 Hainan Xu September 4, 2015 1 /
More informationMemory-Efficient Heterogeneous Speech Recognition Hybrid in GPU-Equipped Mobile Devices
Memory-Efficient Heterogeneous Speech Recognition Hybrid in GPU-Equipped Mobile Devices Alexei V. Ivanov, CTO, Verbumware Inc. GPU Technology Conference, San Jose, March 17, 2015 Autonomous Speech Recognition
More informationApplications of Lexicographic Semirings to Problems in Speech and Language Processing
Applications of Lexicographic Semirings to Problems in Speech and Language Processing Richard Sproat Google, Inc. Izhak Shafran Oregon Health & Science University Mahsa Yarmohammadi Oregon Health & Science
More informationLattice Rescoring for Speech Recognition Using Large Scale Distributed Language Models
Lattice Rescoring for Speech Recognition Using Large Scale Distributed Language Models ABSTRACT Euisok Chung Hyung-Bae Jeon Jeon-Gue Park and Yun-Keun Lee Speech Processing Research Team, ETRI, 138 Gajeongno,
More informationOn LM Heuristics for the Cube Growing Algorithm
On LM Heuristics for the Cube Growing Algorithm David Vilar and Hermann Ney Lehrstuhl für Informatik 6 RWTH Aachen University 52056 Aachen, Germany {vilar,ney}@informatik.rwth-aachen.de Abstract Current
More informationWeighted Finite State Transducers in Automatic Speech Recognition
Weighted Finite State Transducers in Automatic Speech Recognition ZRE lecture 15.04.2015 Mirko Hannemann Slides provided with permission, Daniel Povey some slides from T. Schultz, M. Mohri, M. Riley and
More informationThe QCN System for Egyptian Arabic to English Machine Translation. Presenter: Hassan Sajjad
The QCN System for Egyptian Arabic to English Machine Translation Presenter: Hassan Sajjad QCN Collaboration Ahmed El Kholy Wael Salloum Nizar Habash Ahmed Abdelali Nadir Durrani Francisco Guzmán Preslav
More informationSpeech Recognition Lecture 12: Lattice Algorithms. Cyril Allauzen Google, NYU Courant Institute Slide Credit: Mehryar Mohri
Speech Recognition Lecture 12: Lattice Algorithms. Cyril Allauzen Google, NYU Courant Institute allauzen@cs.nyu.edu Slide Credit: Mehryar Mohri This Lecture Speech recognition evaluation N-best strings
More informationA General-Purpose Rule Extractor for SCFG-Based Machine Translation
A General-Purpose Rule Extractor for SCFG-Based Machine Translation Greg Hanneman, Michelle Burroughs, and Alon Lavie Language Technologies Institute Carnegie Mellon University Fifth Workshop on Syntax
More informationSparse Feature Learning
Sparse Feature Learning Philipp Koehn 1 March 2016 Multiple Component Models 1 Translation Model Language Model Reordering Model Component Weights 2 Language Model.05 Translation Model.26.04.19.1 Reordering
More informationStatistical Machine Translation Part IV Log-Linear Models
Statistical Machine Translation art IV Log-Linear Models Alexander Fraser Institute for Natural Language rocessing University of Stuttgart 2011.11.25 Seminar: Statistical MT Where we have been We have
More informationReport for each of the weighted automata obtained ˆ the number of states; ˆ the number of ɛ-transitions;
Mehryar Mohri Speech Recognition Courant Institute of Mathematical Sciences Homework assignment 3 (Solution) Part 2, 3 written by David Alvarez 1. For this question, it is recommended that you use the
More informationLeft-to-Right Tree-to-String Decoding with Prediction
Left-to-Right Tree-to-String Decoding with Prediction Yang Feng Yang Liu Qun Liu Trevor Cohn Department of Computer Science The University of Sheffield, Sheffield, UK {y.feng, t.cohn}@sheffield.ac.uk State
More informationForest Reranking for Machine Translation with the Perceptron Algorithm
Forest Reranking for Machine Translation with the Perceptron Algorithm Zhifei Li and Sanjeev Khudanpur Center for Language and Speech Processing and Department of Computer Science Johns Hopkins University,
More informationSpeech Technology Using in Wechat
Speech Technology Using in Wechat FENG RAO Powered by WeChat Outline Introduce Algorithm of Speech Recognition Acoustic Model Language Model Decoder Speech Technology Open Platform Framework of Speech
More informationSemantic Word Embedding Neural Network Language Models for Automatic Speech Recognition
Semantic Word Embedding Neural Network Language Models for Automatic Speech Recognition Kartik Audhkhasi, Abhinav Sethy Bhuvana Ramabhadran Watson Multimodal Group IBM T. J. Watson Research Center Motivation
More informationPing-pong decoding Combining forward and backward search
Combining forward and backward search Research Internship 09/ - /0/0 Mirko Hannemann Microsoft Research, Speech Technology (Redmond) Supervisor: Daniel Povey /0/0 Mirko Hannemann / Beam Search Search Errors
More informationWednesday, August 31, Parsers
Parsers How do we combine tokens? Combine tokens ( words in a language) to form programs ( sentences in a language) Not all combinations of tokens are correct programs (not all sentences are grammatically
More informationTraining a Super Model Look-Alike:Featuring Edit Distance, N-Gram Occurrence,and One Reference Translation p.1/40
Training a Super Model Look-Alike: Featuring Edit Distance, N-Gram Occurrence, and One Reference Translation Eva Forsbom, Uppsala University evafo@stp.ling.uu.se MT Summit IX Workshop on Machine Translation
More informationNTT SMT System for IWSLT Katsuhito Sudoh, Taro Watanabe, Jun Suzuki, Hajime Tsukada, and Hideki Isozaki NTT Communication Science Labs.
NTT SMT System for IWSLT 2008 Katsuhito Sudoh, Taro Watanabe, Jun Suzuki, Hajime Tsukada, and Hideki Isozaki NTT Communication Science Labs., Japan Overview 2-stage translation system k-best translation
More informationTransition-Based Dependency Parsing with Stack Long Short-Term Memory
Transition-Based Dependency Parsing with Stack Long Short-Term Memory Chris Dyer, Miguel Ballesteros, Wang Ling, Austin Matthews, Noah A. Smith Association for Computational Linguistics (ACL), 2015 Presented
More informationExam Marco Kuhlmann. This exam consists of three parts:
TDDE09, 729A27 Natural Language Processing (2017) Exam 2017-03-13 Marco Kuhlmann This exam consists of three parts: 1. Part A consists of 5 items, each worth 3 points. These items test your understanding
More informationCompiler Construction
Compiler Construction Lecture 2: Lexical Analysis I (Introduction) Thomas Noll Lehrstuhl für Informatik 2 (Software Modeling and Verification) noll@cs.rwth-aachen.de http://moves.rwth-aachen.de/teaching/ss-14/cc14/
More informationThe HDU Discriminative SMT System for Constrained Data PatentMT at NTCIR10
The HDU Discriminative SMT System for Constrained Data PatentMT at NTCIR10 Patrick Simianer, Gesa Stupperich, Laura Jehl, Katharina Wäschle, Artem Sokolov, Stefan Riezler Institute for Computational Linguistics,
More informationCompiler Construction 2016/2017 Syntax Analysis
Compiler Construction 2016/2017 Syntax Analysis Peter Thiemann November 2, 2016 Outline 1 Syntax Analysis Recursive top-down parsing Nonrecursive top-down parsing Bottom-up parsing Syntax Analysis tokens
More informationA Comparison of Sequence-Trained Deep Neural Networks and Recurrent Neural Networks Optical Modeling For Handwriting Recognition
A Comparison of Sequence-Trained Deep Neural Networks and Recurrent Neural Networks Optical Modeling For Handwriting Recognition Théodore Bluche, Hermann Ney, Christopher Kermorvant SLSP 14, Grenoble October
More informationSpatial Data Structures
Spatial Data Structures Hierarchical Bounding Volumes Regular Grids Octrees BSP Trees Constructive Solid Geometry (CSG) [Angel 9.10] Outline Ray tracing review what rays matter? Ray tracing speedup faster
More informationDiscriminative Training of Decoding Graphs for Large Vocabulary Continuous Speech Recognition
Discriminative Training of Decoding Graphs for Large Vocabulary Continuous Speech Recognition by Hong-Kwang Jeff Kuo, Brian Kingsbury (IBM Research) and Geoffry Zweig (Microsoft Research) ICASSP 2007 Presented
More informationMonday, September 13, Parsers
Parsers Agenda Terminology LL(1) Parsers Overview of LR Parsing Terminology Grammar G = (Vt, Vn, S, P) Vt is the set of terminals Vn is the set of non-terminals S is the start symbol P is the set of productions
More informationContext-Free Languages and Parse Trees
Context-Free Languages and Parse Trees Mridul Aanjaneya Stanford University July 12, 2012 Mridul Aanjaneya Automata Theory 1/ 41 Context-Free Grammars A context-free grammar is a notation for describing
More informationTraining and Evaluating Error Minimization Rules for Statistical Machine Translation
Training and Evaluating Error Minimization Rules for Statistical Machine Translation Ashish Venugopal School of Computer Science Carnegie Mellon University arv@andrew.cmu.edu Andreas Zollmann School of
More informationScanning methods and language modeling for binary switch typing
Scanning methods and language modeling for binary switch typing Brian Roark, Jacques de Villiers, Christopher Gibbons and Melanie Fried-Oken Center for Spoken Language Understanding Child Development &
More informationCMU-UKA Syntax Augmented Machine Translation
Outline CMU-UKA Syntax Augmented Machine Translation Ashish Venugopal, Andreas Zollmann, Stephan Vogel, Alex Waibel InterACT, LTI, Carnegie Mellon University Pittsburgh, PA Outline Outline 1 2 3 4 Issues
More informationBottom-up parsing. Bottom-Up Parsing. Recall. Goal: For a grammar G, withstartsymbols, any string α such that S α is called a sentential form
Bottom-up parsing Bottom-up parsing Recall Goal: For a grammar G, withstartsymbols, any string α such that S α is called a sentential form If α V t,thenα is called a sentence in L(G) Otherwise it is just
More informationRefactored Moses. Hieu Hoang MT Marathon Prague August 2013
Refactored Moses Hieu Hoang MT Marathon Prague August 2013 What did you Refactor? Decoder Feature Func?on Framework moses.ini format Simplify class structure Deleted func?onality NOT decoding algorithms
More informationChapter 4. Lexical and Syntax Analysis
Chapter 4 Lexical and Syntax Analysis Chapter 4 Topics Introduction Lexical Analysis The Parsing Problem Recursive-Descent Parsing Bottom-Up Parsing Copyright 2012 Addison-Wesley. All rights reserved.
More informationIntroduction to Modeling. Lecture Overview
Lecture Overview What is a Model? Uses of Modeling The Modeling Process Pose the Question Define the Abstractions Create the Model Analyze the Data Model Representations * Queuing Models * Petri Nets *
More informationLearning Non-linear Features for Machine Translation Using Gradient Boosting Machines
Learning Non-linear Features for Machine Translation Using Gradient Boosting Machines Kristina Toutanova Microsoft Research Redmond, WA 98502 kristout@microsoft.com Byung-Gyu Ahn Johns Hopkins University
More informationThe CKY Parsing Algorithm and PCFGs. COMP-599 Oct 12, 2016
The CKY Parsing Algorithm and PCFGs COMP-599 Oct 12, 2016 Outline CYK parsing PCFGs Probabilistic CYK parsing 2 CFGs and Constituent Trees Rules/productions: S VP this VP V V is rules jumps rocks Trees:
More informationCube Pruning as Heuristic Search
Cube Pruning as Heuristic Search Mark Hopkins and Greg Langmead Language Weaver, Inc. 4640 Admiralty Way, Suite 1210 Marina del Rey, CA 90292 {mhopkins,glangmead}@languageweaver.com Abstract Cube pruning
More informationScalable Trigram Backoff Language Models
Scalable Trigram Backoff Language Models Kristie Seymore Ronald Rosenfeld May 1996 CMU-CS-96-139 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 This material is based upon work
More informationStabilizing Minimum Error Rate Training
Stabilizing Minimum Error Rate Training George Foster and Roland Kuhn National Research Council Canada first.last@nrc.gc.ca Abstract The most commonly used method for training feature weights in statistical
More informationContext-free grammars
Context-free grammars Section 4.2 Formal way of specifying rules about the structure/syntax of a program terminals - tokens non-terminals - represent higher-level structures of a program start symbol,
More informationEFFICIENT LATTICE RESCORING USING RECURRENT NEURAL NETWORK LANGUAGE MODELS. X.Liu,Y.Wang,X.Chen,M.J.F.Gales & P.C.Woodland
EFFICIENT LATTICE RESCORING USING RECURRENT NEURAL NETWORK LANGUAGE MODELS X.Liu,Y.Wang,X.Chen,M.J.F.Gales & P.C.Woodland Cambridge University Engineering Dept, Trumpington St., Cambridge, CB2 1PZ U.K.
More informationWFST: Weighted Finite State Transducer. September 12, 2017 Prof. Marie Meteer
+ WFST: Weighted Finite State Transducer September 12, 217 Prof. Marie Meteer + FSAs: A recurring structure in speech 2 Phonetic HMM Viterbi trellis Language model Pronunciation modeling + The language
More informationMoses version 2.1 Release Notes
Moses version 2.1 Release Notes Overview The document is the release notes for the Moses SMT toolkit, version 2.1. It describes the changes to toolkit since version 1.0 from January 2013. The aim during
More informationCompiler Construction: Parsing
Compiler Construction: Parsing Mandar Mitra Indian Statistical Institute M. Mitra (ISI) Parsing 1 / 33 Context-free grammars. Reference: Section 4.2 Formal way of specifying rules about the structure/syntax
More informationTuring Machines. A transducer is a finite state machine (FST) whose output is a string and not just accept or reject.
Turing Machines Transducers: A transducer is a finite state machine (FST) whose output is a string and not just accept or reject. Each transition of an FST is labeled with two symbols, one designating
More informationRandom Restarts in Minimum Error Rate Training for Statistical Machine Translation
Random Restarts in Minimum Error Rate Training for Statistical Machine Translation Robert C. Moore and Chris Quirk Microsoft Research Redmond, WA 98052, USA bobmoore@microsoft.com, chrisq@microsoft.com
More informationUnit 4: Formal Verification
Course contents Unit 4: Formal Verification Logic synthesis basics Binary-decision diagram (BDD) Verification Logic optimization Technology mapping Readings Chapter 11 Unit 4 1 Logic Synthesis & Verification
More information4. Lexical and Syntax Analysis
4. Lexical and Syntax Analysis 4.1 Introduction Language implementation systems must analyze source code, regardless of the specific implementation approach Nearly all syntax analysis is based on a formal
More informationYou will likely want to log into your assigned x-node from yesterday. Part 1: Shake-and-bake language generation
FSM Tutorial I assume that you re using bash as your shell; if not, then type bash before you start (you can use csh-derivatives if you want, but your mileage may vary). You will likely want to log into
More informationAdvanced Search Algorithms
CS11-747 Neural Networks for NLP Advanced Search Algorithms Daniel Clothiaux https://phontron.com/class/nn4nlp2017/ Why search? So far, decoding has mostly been greedy Chose the most likely output from
More informationThe Parsing Problem (cont d) Recursive-Descent Parsing. Recursive-Descent Parsing (cont d) ICOM 4036 Programming Languages. The Complexity of Parsing
ICOM 4036 Programming Languages Lexical and Syntax Analysis Lexical Analysis The Parsing Problem Recursive-Descent Parsing Bottom-Up Parsing This lecture covers review questions 14-27 This lecture covers
More informationVIVA QUESTIONS WITH ANSWERS
VIVA QUESTIONS WITH ANSWERS 1. What is a compiler? A compiler is a program that reads a program written in one language the source language and translates it into an equivalent program in another language-the
More informationFormal Languages and Compilers Lecture IV: Regular Languages and Finite. Finite Automata
Formal Languages and Compilers Lecture IV: Regular Languages and Finite Automata Free University of Bozen-Bolzano Faculty of Computer Science POS Building, Room: 2.03 artale@inf.unibz.it http://www.inf.unibz.it/
More information4. Lexical and Syntax Analysis
4. Lexical and Syntax Analysis 4.1 Introduction Language implementation systems must analyze source code, regardless of the specific implementation approach Nearly all syntax analysis is based on a formal
More informationOutline GIZA++ Moses. Demo. Steps Output files. Training pipeline Decoder
GIZA++ and Moses Outline GIZA++ Steps Output files Moses Training pipeline Decoder Demo GIZA++ A statistical machine translation toolkit used to train IBM Models 1-5 (moses only uses output of IBM Model-1)
More informationMS WORD. You can use it for writing letters, reports and so on.
MS WORD MS WORD 2 You can use it for writing letters, reports and so on. Starting Word application 3 To start MS. Word do the following: 1. From the Start button on the taskbar, select All Programs. 2.
More informationCSE P 501 Compilers. Parsing & Context-Free Grammars Hal Perkins Winter /15/ Hal Perkins & UW CSE C-1
CSE P 501 Compilers Parsing & Context-Free Grammars Hal Perkins Winter 2008 1/15/2008 2002-08 Hal Perkins & UW CSE C-1 Agenda for Today Parsing overview Context free grammars Ambiguous grammars Reading:
More informationFormal languages and computation models
Formal languages and computation models Guy Perrier Bibliography John E. Hopcroft, Rajeev Motwani, Jeffrey D. Ullman - Introduction to Automata Theory, Languages, and Computation - Addison Wesley, 2006.
More informationA left-sentential form is a sentential form that occurs in the leftmost derivation of some sentence.
Bottom-up parsing Recall For a grammar G, with start symbol S, any string α such that S α is a sentential form If α V t, then α is a sentence in L(G) A left-sentential form is a sentential form that occurs
More informationThe analysis part breaks up the source program into constituent pieces and creates an intermediate representation of the source program.
COMPILER DESIGN 1. What is a compiler? A compiler is a program that reads a program written in one language the source language and translates it into an equivalent program in another language-the target
More informationType Checking. Outline. General properties of type systems. Types in programming languages. Notation for type rules.
Outline Type Checking General properties of type systems Types in programming languages Notation for type rules Logical rules of inference Common type rules 2 Static Checking Refers to the compile-time
More informationLarge-Scale Discriminative Training for Statistical Machine Translation Using Held-Out Line Search
Large-Scale Discriminative Training for Statistical Machine Translation Using Held-Out Line Search Jeffrey Flanigan Chris Dyer Jaime Carbonell Language Technologies Institute Carnegie Mellon University
More informationMOSES. Statistical Machine Translation System. User Manual and Code Guide. Philipp Koehn University of Edinburgh
MOSES Statistical Machine Translation System User Manual and Code Guide Philipp Koehn pkoehn@inf.ed.ac.uk University of Edinburgh Abstract This document serves as user manual and code guide for the Moses
More informationOutline. General properties of type systems. Types in programming languages. Notation for type rules. Common type rules. Logical rules of inference
Type Checking Outline General properties of type systems Types in programming languages Notation for type rules Logical rules of inference Common type rules 2 Static Checking Refers to the compile-time
More informationParsing with Dynamic Programming
CS11-747 Neural Networks for NLP Parsing with Dynamic Programming Graham Neubig Site https://phontron.com/class/nn4nlp2017/ Two Types of Linguistic Structure Dependency: focus on relations between words
More informationBetter Synchronous Binarization for Machine Translation
Better Synchronous Binarization for Machine Translation Tong Xiao *, Mu Li +, Dongdong Zhang +, Jingbo Zhu *, Ming Zhou + * Natural Language Processing Lab Northeastern University Shenyang, China, 110004
More informationA Deep Relevance Matching Model for Ad-hoc Retrieval
A Deep Relevance Matching Model for Ad-hoc Retrieval Jiafeng Guo 1, Yixing Fan 1, Qingyao Ai 2, W. Bruce Croft 2 1 CAS Key Lab of Web Data Science and Technology, Institute of Computing Technology, Chinese
More informationComposition Systems. Composition Systems. Contents. Contents. What s s in this paper. Introduction. On-Line Character Recognition.
Contents S. Geman, D.F. Potter, Z. Chi Presented by Haibin Ling 12. 2. 2003 Definition: Compositionality refers to the evident ability of humans to represent entities as hierarchies of parts,, with these
More informationCS 288: Statistical NLP Assignment 1: Language Modeling
CS 288: Statistical NLP Assignment 1: Language Modeling Due September 12, 2014 Collaboration Policy You are allowed to discuss the assignment with other students and collaborate on developing algorithms
More informationAnnual Public Report - Project Year 2 November 2012
November 2012 Grant Agreement number: 247762 Project acronym: FAUST Project title: Feedback Analysis for User Adaptive Statistical Translation Funding Scheme: FP7-ICT-2009-4 STREP Period covered: from
More informationCompiler Construction
Compiler Construction Thomas Noll Software Modeling and Verification Group RWTH Aachen University https://moves.rwth-aachen.de/teaching/ss-16/cc/ Conceptual Structure of a Compiler Source code x1 := y2
More informationThe Prague Bulletin of Mathematical Linguistics NUMBER 91 JANUARY
The Prague Bulletin of Mathematical Linguistics NUMBER 9 JANUARY 009 79 88 Z-MERT: A Fully Configurable Open Source Tool for Minimum Error Rate Training of Machine Translation Systems Omar F. Zaidan Abstract
More informationLast lecture CMSC330. This lecture. Finite Automata: States. Finite Automata. Implementing Regular Expressions. Languages. Regular expressions
Last lecture CMSC330 Finite Automata Languages Sets of strings Operations on languages Regular expressions Constants Operators Precedence 1 2 Finite automata States Transitions Examples Types This lecture
More informationLSTM for Language Translation and Image Captioning. Tel Aviv University Deep Learning Seminar Oran Gafni & Noa Yedidia
1 LSTM for Language Translation and Image Captioning Tel Aviv University Deep Learning Seminar Oran Gafni & Noa Yedidia 2 Part I LSTM for Language Translation Motivation Background (RNNs, LSTMs) Model
More informationCOMP-421 Compiler Design. Presented by Dr Ioanna Dionysiou
COMP-421 Compiler Design Presented by Dr Ioanna Dionysiou Administrative! [ALSU03] Chapter 3 - Lexical Analysis Sections 3.1-3.4, 3.6-3.7! Reading for next time [ALSU03] Chapter 3 Copyright (c) 2010 Ioanna
More informationpycdec: A Python Interface to cdec
Carnegie Mellon University Research Showcase @ CMU Language Technologies Institute School of Computer Science 10-2012 pycdec: A Python Interface to cdec Victor Chahuneau Carnegie Mellon University Noah
More information