Joint Decoding with Multiple Translation Models

Size: px
Start display at page:

Download "Joint Decoding with Multiple Translation Models"

Transcription

1 Joint Decoding with Multiple Translation Models Yang Liu, Haitao Mi, Yang Feng, and Qun Liu Institute of Computing Technology, Chinese Academy of ciences 8/10/2009 ACL/IJCNLP 2009, ingapore 1

2 ystem Combination ystem 1 E1 ystem 2 E2 f Combiner e ystem n En decoding? postprocessing 8/10/2009 ACL/IJCNLP 2009, ingapore 2

3 This Work We propose a technique called joint decoding to combine different models directly in the decoding phase. Our preliminary work shows promising results. 8/10/2009 ACL/IJCNLP 2009, ingapore 3

4 Translation Hypergraph fabiao yanjiang give a talk give talks give 0-1 talk 1-2 8/10/2009 ACL/IJCNLP 2009, ingapore 4

5 Consensus Translations give talks give a talk give a talk give talks give a talk give a speech give 0-1 talks 1-2 give 0-1 talk 1-2 give 0-1 talk 1-2 phrase-based hierarchical phrase-based tree-to-string 8/10/2009 ACL/IJCNLP 2009, ingapore 5

6 haring Nodes give a speech give a talk give talks give 0-1 talk 1-2 talks 1-2 8/10/2009 ACL/IJCNLP 2009, ingapore 6

7 coring a Translation target sentence source sentence pe ( f) = ped, f d ( ef, ) ( ) one derivation the set of derivations that translate f into e a derivation can come from any model! 8/10/2009 ACL/IJCNLP 2009, ingapore 7

8 MDD and MTD ( ) p e f = d ( e, f ) exp λihi de,, f i Z ( ) Blunsom et al. (2008) eˆ = argmaxe exp λihi( de,, f ) d ( e, f ) i argmax ed, λihi( de,, f ) i max-translation decoding max-derivation decoding 8/10/2009 ACL/IJCNLP 2009, ingapore 8

9 An Example of MTD model name feature weight value p(e f) 0.1 hier p(f e) l(e f) exp(3.7) l(f e) 0.3 rc 3 t2s p(e f) p(f e) l(e f) exp(4.8) (exp(3.7) + exp(4.8)) exp(3.7) l(f e) 0.2 rc 4 const lm wc exp(3.7) 8/10/2009 ACL/IJCNLP 2009, ingapore 9

10 Joint Decoding fabiao yanjiang /10/2009 ACL/IJCNLP 2009, ingapore 10

11 Joint Decoding fabiao yanjiang give 0-1 8/10/2009 ACL/IJCNLP 2009, ingapore 11

12 Joint Decoding fabiao yanjiang give 0-1 talk 1-2 8/10/2009 ACL/IJCNLP 2009, ingapore 12

13 Joint Decoding fabiao yanjiang give 0-1 talk 1-2 talks 1-2 8/10/2009 ACL/IJCNLP 2009, ingapore 13

14 Joint Decoding fabiao yanjiang give 0-1 talk 1-2 talks 1-2 8/10/2009 ACL/IJCNLP 2009, ingapore 14

15 Joint Decoding fabiao yanjiang give a speech give a talk give talks give 0-1 talk 1-2 8/10/2009 ACL/IJCNLP 2009, ingapore 15

16 Joint Decoding fabiao yanjiang give a talk a pruned packed hypergraph give 0-1 talk 1-2 8/10/2009 ACL/IJCNLP 2009, ingapore 16

17 haring Hyperedges give a talk give 0-1 talk 1-2 8/10/2009 ACL/IJCNLP 2009, ingapore 17

18 Joint Decoding with Different Rules VP VV NN fabiao yanjiang /10/2009 ACL/IJCNLP 2009, ingapore 18

19 Joint Decoding with Different Rules VP X -> <fabiao, give> VV NN fabiao yanjiang give 0-1 8/10/2009 ACL/IJCNLP 2009, ingapore 19

20 Joint Decoding with Different Rules VV VP NN X -> <fabiao, give> X -> <yanjiang, talk> fabiao yanjiang give 0-1 talk 1-2 8/10/2009 ACL/IJCNLP 2009, ingapore 20

21 Joint Decoding with Different Rules (VP (VV:x1) (NN:x2)) -> x1 a x2 VV VP NN X -> <fabiao, give> X -> <yanjiang, talk> fabiao yanjiang give a talk give 0-1 talk 1-2 8/10/2009 ACL/IJCNLP 2009, ingapore 21

22 An Example of MDD model name feature weight value p(e f) 0.1 p(f e) 0.2 hier l(e f) 0.1 l(f e) 0.3 rc 2 p(e f) p(f e) t2s l(e f) 0.3 l(f e) 0.2 rc 1 const lm wc /10/2009 ACL/IJCNLP 2009, ingapore 22

23 haring Matrix Phrase Hiero T2 2T T2T Phrase node, edge node, edge node, edge node node Hiero node, edge node, edge node, edge node node T2 node, edge node, edge node, edge node node 2T node node node node, edge node, edge T2T node node node node, edge node, edge 8/10/2009 ACL/IJCNLP 2009, ingapore 23

24 How to Tune Feature Weights for MTD? model name feature weight value hier p(e f) p(f e) l(e f) eˆ = argmaxe exp λihi( d, e, f ) d ( e, f ) i l(f e) 0.3 rc 3 p(e f) p(f e) (exp(3.7) + exp(4.8)) exp(3.7) t2s l(e f) 0.3 l(f e) 0.2 rc 4 const lm wc /10/2009 ACL/IJCNLP 2009, ingapore 24

25 MERT for MDD f e1 e2 e3 d d d e1 e3 e2 8/10/2009 ACL/IJCNLP 2009, ingapore 25

26 MERT for MTD f e1 e2 e3 model 1 model 2 d d d d d d /10/2009 ACL/IJCNLP 2009, ingapore 26

27 Curves e1 e2 ( ) K = ak f x e + k= 1 x b k e3 8/10/2009 ACL/IJCNLP 2009, ingapore 27

28 etup Models Hierarchical phrase-based (Chiang, 2005) Tree-to-string (Liu et al., 2006) Training set: FBI (6.9M + 8.9M) Language model: 4-gram trained on GIGAWORD Xinhua portion Development set: NIT 2002 C2E Test set: NIT 2005 C2E 8/10/2009 ACL/IJCNLP 2009, ingapore 28

29 Individual Decoding Vs. Joint Decoding Model haring Max-derivation Time BLEU Max-translation Time BLEU Hiero T both node node & edge /10/2009 ACL/IJCNLP 2009, ingapore 29

30 Compared with ystem Combination Method Model BLEU individual Hiero T system comb. both joint both /10/2009 ACL/IJCNLP 2009, ingapore 30

31 Individual Training Vs. Joint Training Training individual joint Max-derivation Max-translation /10/2009 ACL/IJCNLP 2009, ingapore 31

32 Conclusion and Future Work We have presented a framework for combining different translation models in the decoding phrase. Future work Including more models Forced decoding Hypergraph-based MERT (Kumar et al., 2009) 8/10/2009 ACL/IJCNLP 2009, ingapore 32

33 Thanks! 8/10/2009 ACL/IJCNLP 2009, ingapore 33

Joint Decoding with Multiple Translation Models

Joint Decoding with Multiple Translation Models Joint Decoding with Multiple Translation Models Yang Liu and Haitao Mi and Yang Feng and Qun Liu Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of

More information

Tuning. Philipp Koehn presented by Gaurav Kumar. 28 September 2017

Tuning. 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 information

An Unsupervised Model for Joint Phrase Alignment and Extraction

An Unsupervised Model for Joint Phrase Alignment and Extraction An Unsupervised Model for Joint Phrase Alignment and Extraction Graham Neubig 1,2, Taro Watanabe 2, Eiichiro Sumita 2, Shinsuke Mori 1, Tatsuya Kawahara 1 1 Graduate School of Informatics, Kyoto University

More information

Left-to-Right Tree-to-String Decoding with Prediction

Left-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 information

Forest-based Algorithms in

Forest-based Algorithms in Forest-based Algorithms in Natural Language Processing Liang Huang overview of Ph.D. work done at Penn (and ISI, ICT) INSTITUTE OF COMPUTING TECHNOLOGY includes joint work with David Chiang, Kevin Knight,

More information

Machine Translation with Lattices and Forests

Machine Translation with Lattices and Forests Machine Translation with Lattices and Forests Haitao Mi Liang Huang Qun Liu Key Lab. of Intelligent Information Processing Information Sciences Institute Institute of Computing Technology Viterbi School

More information

Forest-based Translation Rule Extraction

Forest-based Translation Rule Extraction Forest-based Translation Rule Extraction Haitao Mi 1 1 Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704, Beijing 100190, China

More information

Hierarchical Phrase-Based Translation with WFSTs. Weighted Finite State Transducers

Hierarchical Phrase-Based Translation with WFSTs. Weighted Finite State Transducers 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

More information

Better 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 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 information

THE CUED NIST 2009 ARABIC-ENGLISH SMT SYSTEM

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 information

A General-Purpose Rule Extractor for SCFG-Based Machine Translation

A 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 information

Efficient 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 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 information

K-best Parsing Algorithms

K-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 information

Constituency to Dependency Translation with Forests

Constituency to Dependency Translation with Forests Constituency to Dependency Translation with Forests Haitao Mi and Qun Liu Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704,

More information

NTT SMT System for IWSLT Katsuhito Sudoh, Taro Watanabe, Jun Suzuki, Hajime Tsukada, and Hideki Isozaki NTT Communication Science Labs.

NTT 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 information

Sparse Feature Learning

Sparse 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 information

A 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. 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 information

Forest-Based Search Algorithms

Forest-Based Search Algorithms Forest-Based Search Algorithms for Parsing and Machine Translation Liang Huang University of Pennsylvania Google Research, March 14th, 2008 Search in NLP is not trivial! I saw her duck. Aravind Joshi 2

More information

Forest Reranking for Machine Translation with the Perceptron Algorithm

Forest 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 information

Discriminative Training for Phrase-Based Machine Translation

Discriminative Training for Phrase-Based Machine Translation Discriminative Training for Phrase-Based Machine Translation Abhishek Arun 19 April 2007 Overview 1 Evolution from generative to discriminative models Discriminative training Model Learning schemes Featured

More information

Word Lattice Reranking for Chinese Word Segmentation and Part-of-Speech Tagging

Word Lattice Reranking for Chinese Word Segmentation and Part-of-Speech Tagging Word Lattice Reranking for Chinese Word Segmentation and Part-of-Speech Tagging Wenbin Jiang Haitao Mi Qun Liu Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy

More information

Fast Generation of Translation Forest for Large-Scale SMT Discriminative Training

Fast Generation of Translation Forest for Large-Scale SMT Discriminative Training Fast Generation of Translation Forest for Large-Scale SMT Discriminative Training Xinyan Xiao, Yang Liu, Qun Liu, and Shouxun Lin Key Laboratory of Intelligent Information Processing Institute of Computing

More information

Refactored Moses. Hieu Hoang MT Marathon Prague August 2013

Refactored 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 information

The HDU Discriminative SMT System for Constrained Data PatentMT at NTCIR10

The 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 information

Improving Tree-to-Tree Translation with Packed Forests

Improving Tree-to-Tree Translation with Packed Forests Improving Tree-to-Tree Translation with Packed Forests Yang Liu and Yajuan Lü and Qun Liu Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences

More information

TALP: 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 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 information

CMU-UKA Syntax Augmented Machine Translation

CMU-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 information

Learning Non-linear Features for Machine Translation Using Gradient Boosting Machines

Learning 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 information

Parsing with Dynamic Programming

Parsing 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 information

Marcello Federico MMT Srl / FBK Trento, Italy

Marcello Federico MMT Srl / FBK Trento, Italy Marcello Federico MMT Srl / FBK Trento, Italy Proceedings for AMTA 2018 Workshop: Translation Quality Estimation and Automatic Post-Editing Boston, March 21, 2018 Page 207 Symbiotic Human and Machine Translation

More information

Hierarchical Phrase-Based Translation with Weighted Finite State Transducers

Hierarchical 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 information

D6.1.2: Second report on scientific evaluations

D6.1.2: Second report on scientific evaluations D6.1.2: Second report on scientific evaluations UPVLC, XEROX, JSI-K4A, RWTH, EML and DDS Distribution: Public translectures Transcription and Translation of Video Lectures ICT Project 287755 Deliverable

More information

Language in 10 minutes

Language in 10 minutes Language in 10 minutes http://mt-class.org/jhu/lin10.html By Friday: Group up (optional, max size 2), choose a language (not one y all speak) and a date First presentation: Yuan on Thursday Yuan will start

More information

Locally Training the Log-Linear Model for SMT

Locally Training the Log-Linear Model for SMT Locally Training the Log-Linear Model for SMT Lemao Liu 1, Hailong Cao 1, Taro Watanabe 2, Tiejun Zhao 1, Mo Yu 1, CongHui Zhu 1 1 School of Computer Science and Technology Harbin Institute of Technology,

More information

Reassessment of the Role of Phrase Extraction in PBSMT

Reassessment of the Role of Phrase Extraction in PBSMT Reassessment of the Role of Phrase Extraction in Francisco Guzmán CCIR-ITESM guzmanhe@gmail.com Qin Gao LTI-CMU qing@cs.cmu.edu Stephan Vogel LTI-CMU stephan.vogel@cs.cmu.edu Presented by: Nguyen Bach

More information

Homework 1. Leaderboard. Read through, submit the default output. Time for questions on Tuesday

Homework 1. Leaderboard. Read through, submit the default output. Time for questions on Tuesday Homework 1 Leaderboard Read through, submit the default output Time for questions on Tuesday Agenda Focus on Homework 1 Review IBM Models 1 & 2 Inference (compute best alignment from a corpus given model

More information

Local Phrase Reordering Models for Statistical Machine Translation

Local 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 information

Moses version 2.1 Release Notes

Moses 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 information

Speech Technology Using in Wechat

Speech 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 information

The Prague Bulletin of Mathematical Linguistics NUMBER 91 JANUARY

The 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 information

Type-based MCMC for Sampling Tree Fragments from Forests

Type-based MCMC for Sampling Tree Fragments from Forests Type-based MCMC for Sampling Tree Fragments from Forests Xiaochang Peng and Daniel Gildea Department of Computer Science University of Rochester Rochester, NY 14627 Abstract This paper applies type-based

More information

Large-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 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 information

The 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 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 information

Word Graphs for Statistical Machine Translation

Word 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 information

Moses Version 3.0 Release Notes

Moses Version 3.0 Release Notes Moses Version 3.0 Release Notes Overview The document contains the release notes for the Moses SMT toolkit, version 3.0. It describes the changes to the toolkit since version 2.0 from January 2014. In

More information

A Semi-supervised Word Alignment Algorithm with Partial Manual Alignments

A Semi-supervised Word Alignment Algorithm with Partial Manual Alignments A Semi-supervised Word Alignment Algorithm with Partial Manual Alignments Qin Gao, Nguyen Bach and Stephan Vogel Language Technologies Institute Carnegie Mellon University 000 Forbes Avenue, Pittsburgh

More information

Natural Language Processing

Natural Language Processing Natural Language Processing Spring 2017 Unit 3: Tree Models Lectures 9-11: Context-Free Grammars and Parsing required hard optional Professor Liang Huang liang.huang.sh@gmail.com Big Picture only 2 ideas

More information

Recurrent Neural Nets II

Recurrent Neural Nets II Recurrent Neural Nets II Steven Spielberg Pon Kumar, Tingke (Kevin) Shen Machine Learning Reading Group, Fall 2016 9 November, 2016 Outline 1 Introduction 2 Problem Formulations with RNNs 3 LSTM for Optimization

More information

On LM Heuristics for the Cube Growing Algorithm

On 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 information

Conditioned Generation

Conditioned Generation CS11-747 Neural Networks for NLP Conditioned Generation Graham Neubig Site https://phontron.com/class/nn4nlp2017/ Language Models Language models are generative models of text s ~ P(x) The Malfoys! said

More information

Statistical Machine Translation Part IV Log-Linear Models

Statistical 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 information

Query Lattice for Translation Retrieval

Query Lattice for Translation Retrieval Query Lattice for Translation Retrieval Meiping Dong, Yong Cheng, Yang Liu, Jia Xu, Maosong Sun, Tatsuya Izuha, Jie Hao # State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory

More information

Study and Implementation of CHAMELEON algorithm for Gene Clustering

Study and Implementation of CHAMELEON algorithm for Gene Clustering [1] Study and Implementation of CHAMELEON algorithm for Gene Clustering 1. Motivation Saurav Sahay The vast amount of gathered genomic data from Microarray and other experiments makes it extremely difficult

More information

Transition-Based Dependency Parsing with Stack Long Short-Term Memory

Transition-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 information

Fluency Constraints for Minimum Bayes-Risk Decoding of Statistical Machine Translation Lattices

Fluency 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 information

INF5820/INF9820 LANGUAGE TECHNOLOGICAL APPLICATIONS. Jan Tore Lønning, Lecture 8, 12 Oct

INF5820/INF9820 LANGUAGE TECHNOLOGICAL APPLICATIONS. Jan Tore Lønning, Lecture 8, 12 Oct 1 INF5820/INF9820 LANGUAGE TECHNOLOGICAL APPLICATIONS Jan Tore Lønning, Lecture 8, 12 Oct. 2016 jtl@ifi.uio.no Today 2 Preparing bitext Parameter tuning Reranking Some linguistic issues STMT so far 3 We

More information

Better Synchronous Binarization for Machine Translation

Better 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 information

Recurrent Neural Networks

Recurrent Neural Networks Recurrent Neural Networks 11-785 / Fall 2018 / Recitation 7 Raphaël Olivier Recap : RNNs are magic They have infinite memory They handle all kinds of series They re the basis of recent NLP : Translation,

More information

A Primer on Graph Processing with Bolinas

A Primer on Graph Processing with Bolinas A Primer on Graph Processing with Bolinas J. Andreas, D. Bauer, K. M. Hermann, B. Jones, K. Knight, and D. Chiang August 20, 2013 1 Introduction This is a tutorial introduction to the Bolinas graph processing

More information

A Structured Language Model for Incremental Tree-to-String Translation

A Structured Language Model for Incremental Tree-to-String Translation A Structud Language Model for Incmental Te-to-String Translation Heng Yu 1 1 Institute of Computing Technology. CAS University of Chinese Academy of Sciences yuheng@ict.ac.cn Haitao Mi T.J. Watson Research

More information

Machine Translation in Academia and in the Commercial World: a Contrastive Perspective

Machine Translation in Academia and in the Commercial World: a Contrastive Perspective Machine Translation in Academia and in the Commercial World: a Contrastive Perspective Alon Lavie Research Professor LTI, Carnegie Mellon University Co-founder, President and CTO Safaba Translation Solutions

More information

SampleRank Training for Phrase-Based Machine Translation

SampleRank Training for Phrase-Based Machine Translation SampleRank Training for Phrase-Based Machine Translation Barry Haddow School of Informatics University of Edinburgh bhaddow@inf.ed.ac.uk Abhishek Arun Microsoft UK abarun@microsoft.com Philipp Koehn School

More information

Exact Decoding of Syntactic Translation Models through Lagrangian Relaxation

Exact 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 information

Additive Neural Networks for Statistical Machine Translation

Additive Neural Networks for Statistical Machine Translation Additive Neural Networks for Statistical Machine Translation Lemao Liu 1, Taro Watanabe 2, Eiichiro Sumita 2, Tiejun Zhao 1 1 School of Computer Science and Technology Harbin Institute of Technology (HIT),

More information

BBN System Description for WMT10 System Combination Task

BBN 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 information

CS 288: Statistical NLP Assignment 1: Language Modeling

CS 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 information

PARAMETER SYMBOL MIN MAX Address Access Time

PARAMETER SYMBOL MIN MAX Address Access Time TECHNICAL NOTE TN-00-17 TIMING SPECIFICATION DERATING FOR HIGH CAPACITANCE OUTPUT LOADING Introduction Memory systems are varied in the number of controllers, memory, and other devices that may share a

More information

Experimenting in MT: Moses Toolkit and Eman

Experimenting in MT: Moses Toolkit and Eman Experimenting in MT: Moses Toolkit and Eman Aleš Tamchyna, Ondřej Bojar Institute of Formal and Applied Linguistics Faculty of Mathematics and Physics Charles University, Prague Tue Sept 8, 2015 1 / 30

More information

Hidden Markov Models. Slides adapted from Joyce Ho, David Sontag, Geoffrey Hinton, Eric Xing, and Nicholas Ruozzi

Hidden Markov Models. Slides adapted from Joyce Ho, David Sontag, Geoffrey Hinton, Eric Xing, and Nicholas Ruozzi Hidden Markov Models Slides adapted from Joyce Ho, David Sontag, Geoffrey Hinton, Eric Xing, and Nicholas Ruozzi Sequential Data Time-series: Stock market, weather, speech, video Ordered: Text, genes Sequential

More information

Question of the Day. Machine Translation. Statistical Word Alignment. Centauri/Arcturan (Knight, 1997) Centauri/Arcturan (Knight, 1997)

Question of the Day. Machine Translation. Statistical Word Alignment. Centauri/Arcturan (Knight, 1997) Centauri/Arcturan (Knight, 1997) Question of the Day Is it possible to learn to translate from plain example translations? Machine Translation Statistical Word Alignment Based on slides by Philipp Koehn and Kevin Knight Word Alignment

More information

Bayesian Learning of Phrasal Tree-to-String Templates

Bayesian Learning of Phrasal Tree-to-String Templates Bayesian Learning of Phrasal Tree-to-String Templates Ding Liu and Daniel Gildea Department of Computer Science University of Rochester Rochester, NY 14627 {dliu, gildea}@cs.rochester.edu Abstract We examine

More information

Stabilizing Minimum Error Rate Training

Stabilizing 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 information

Semantic Word Embedding Neural Network Language Models for Automatic Speech Recognition

Semantic 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 information

Optimal Partition with Block-Level Parallelization in C-to-RTL Synthesis for Streaming Applications

Optimal Partition with Block-Level Parallelization in C-to-RTL Synthesis for Streaming Applications Optimal Partition with Block-Level Parallelization in C-to-RTL Synthesis for Streaming Applications Authors: Shuangchen Li, Yongpan Liu, X.Sharon Hu, Xinyu He, Pei Zhang, and Huazhong Yang 2013/01/23 Outline

More information

Automatic Summarization

Automatic Summarization Automatic Summarization CS 769 Guest Lecture Andrew B. Goldberg goldberg@cs.wisc.edu Department of Computer Sciences University of Wisconsin, Madison February 22, 2008 Andrew B. Goldberg (CS Dept) Summarization

More information

Dynamic Convolutional Neural Network for Modelling Sentences NAl Kalchbrenner,Edward Grefenstette, Phil Blunsom

Dynamic Convolutional Neural Network for Modelling Sentences NAl Kalchbrenner,Edward Grefenstette, Phil Blunsom Dynamic Convolutional Neural Network for Modelling Sentences NAl Kalchbrenner,Edward Grefenstette, Phil Blunsom Course-CS671 Presented by- Anurendra Kumar(12147) AIM:-Accurately represent sentences capturing

More information

Machine Translation and Discriminative Models

Machine Translation and Discriminative Models Machine Translation and Discriminative Models Tree-to-tree transfer and Discriminative learning Martin Popel ÚFAL (Institute of Formal and Applied Linguistics) Charles University in Prague March 23rd 2015,

More information

Speeding Up Neural Machine Translation Decoding by Cube Pruning

Speeding Up Neural Machine Translation Decoding by Cube Pruning Speeding Up Neural Machine Translation Decoding by Cube Pruning Wen Zhang 1,2 Liang Huang 3,4 Yang Feng 1,2 Lei Shen 1,2 Qun Liu 5,1 1 Key Laboratory of Intelligent Information Processing Institute of

More information

Automatic Determination of Number of clusters for creating templates in Example-Based Machine Translation

Automatic Determination of Number of clusters for creating templates in Example-Based Machine Translation [EAMT May 2010 St Raphael, France] Automatic Determination of Number of clusters for creating templates in Example-Based Machine Translation Rashmi Gangadharaiah rgangadh@cs.cmu.edu Ralf D. Brown ralf@cs.cmu.edu

More information

How to Build Optimized ML Applications with Arm Software

How to Build Optimized ML Applications with Arm Software How to Build Optimized ML Applications with Arm Software Arm Technical Symposia 2018 ML Group Overview Today we will talk about applied machine learning (ML) on Arm. My aim for today is to show you just

More information

A System of Exploiting and Building Homogeneous and Large Resources for the Improvement of Vietnamese-Related Machine Translation Quality

A System of Exploiting and Building Homogeneous and Large Resources for the Improvement of Vietnamese-Related Machine Translation Quality A System of Exploiting and Building Homogeneous and Large Resources for the Improvement of Vietnamese-Related Machine Translation Quality Huỳnh Công Pháp 1 and Nguyễn Văn Bình 2 The University of Danang

More information

Forest-based Neural Machine Translation. Chunpeng Ma, Akihiro Tamura, Masao Utiyama, Tiejun Zhao, EiichiroSumita

Forest-based Neural Machine Translation. Chunpeng Ma, Akihiro Tamura, Masao Utiyama, Tiejun Zhao, EiichiroSumita Forest-based Neural Machine Translation Chunpeng Ma, Akihiro Tamura, Masao Utiyama, Tiejun Zhao, EiichiroSumita Motivation Key point: Syntactic Information To use or not to use? string-to-string model

More information

SPEECH TRANSLATION: THEORY AND PRACTICES

SPEECH TRANSLATION: THEORY AND PRACTICES SPEECH TRANSLATION: THEORY AND PRACTICES Bowen Zhou and Xiaodong He zhou@us.ibm.com xiaohe@microsoft.com May 27 th 2013 @ ICASSP 2013 Universal Translator: dream (will) come true or yet another over promise?

More information

Scanning methods and language modeling for binary switch typing

Scanning 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 information

Random Restarts in Minimum Error Rate Training for Statistical Machine Translation

Random 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 information

Prototype Selection for Handwritten Connected Digits Classification

Prototype Selection for Handwritten Connected Digits Classification 2009 0th International Conference on Document Analysis and Recognition Prototype Selection for Handwritten Connected Digits Classification Cristiano de Santana Pereira and George D. C. Cavalcanti 2 Federal

More information

MOSES. 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 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 information

Multicast Routing : Computer Networking. Example Applications. Overview

Multicast Routing : Computer Networking. Example Applications. Overview Multicast outing 5-744: Computer Networking Unicast: one source to one estination Multicast: one source to many estinations Two main functions: Efficient ata istribution Logical naming of a group L-0 Multicast

More information

Blind Measurement of Blocking Artifact in Images

Blind Measurement of Blocking Artifact in Images The University of Texas at Austin Department of Electrical and Computer Engineering EE 38K: Multidimensional Digital Signal Processing Course Project Final Report Blind Measurement of Blocking Artifact

More information

A Quantitative Analysis of Reordering Phenomena

A Quantitative Analysis of Reordering Phenomena A Quantitative Analysis of Reordering Phenomena Alexandra Birch Phil Blunsom Miles Osborne a.c.birch-mayne@sms.ed.ac.uk pblunsom@inf.ed.ac.uk miles@inf.ed.ac.uk University of Edinburgh 10 Crichton Street

More information

Query by Singing/Humming System Based on Deep Learning

Query by Singing/Humming System Based on Deep Learning Query by Singing/Humming System Based on Deep Learning Jia-qi Sun * and Seok-Pil Lee** *Department of Computer Science, Graduate School, Sangmyung University, Seoul, Korea. ** Department of Electronic

More information

Structured Prediction Basics

Structured Prediction Basics CS11-747 Neural Networks for NLP Structured Prediction Basics Graham Neubig Site https://phontron.com/class/nn4nlp2017/ A Prediction Problem I hate this movie I love this movie very good good neutral bad

More information

(Multinomial) Logistic Regression + Feature Engineering

(Multinomial) Logistic Regression + Feature Engineering -6 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University (Multinomial) Logistic Regression + Feature Engineering Matt Gormley Lecture 9 Feb.

More information

Algorithms for NLP. Machine Translation. Taylor Berg-Kirkpatrick CMU Slides: Dan Klein UC Berkeley

Algorithms for NLP. Machine Translation. Taylor Berg-Kirkpatrick CMU Slides: Dan Klein UC Berkeley Algorithms for NLP Machine Translation Taylor Berg-Kirkpatrick CMU Slides: Dan Klein UC Berkeley Machine Translation Machine Translation: Examples Levels of Transfer Word-Level MT: Examples la politique

More information

Chapter 3. Speech segmentation. 3.1 Preprocessing

Chapter 3. Speech segmentation. 3.1 Preprocessing , as done in this dissertation, refers to the process of determining the boundaries between phonemes in the speech signal. No higher-level lexical information is used to accomplish this. This chapter presents

More information

A Study of MatchPyramid Models on Ad hoc Retrieval

A Study of MatchPyramid Models on Ad hoc Retrieval A Study of MatchPyramid Models on Ad hoc Retrieval Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Xueqi Cheng Institute of Computing Technology, Chinese Academy of Sciences Text Matching Many text based

More information

The Mathematics Behind Neural Networks

The Mathematics Behind Neural Networks The Mathematics Behind Neural Networks Pattern Recognition and Machine Learning by Christopher M. Bishop Student: Shivam Agrawal Mentor: Nathaniel Monson Courtesy of xkcd.com The Black Box Training the

More information

MSA220 - Statistical Learning for Big Data

MSA220 - Statistical Learning for Big Data MSA220 - Statistical Learning for Big Data Lecture 13 Rebecka Jörnsten Mathematical Sciences University of Gothenburg and Chalmers University of Technology Clustering Explorative analysis - finding groups

More information

PowerPAQ-300W-230V-PROG-DALI-BI PowerPAQ-540W-230V-PROG-DALI-1_10V-BI PRODUCT DESCRIPTION POWERPAQ HPLED.

PowerPAQ-300W-230V-PROG-DALI-BI PowerPAQ-540W-230V-PROG-DALI-1_10V-BI PRODUCT DESCRIPTION POWERPAQ HPLED. PowerPAQ-3W-23V-PROG-DALI-BI PRODUCT DESCRIPTION Viapaq Lighting s PowerPAQ drivers have especially been designed for high bay-, flood- & sports lighting applications. Those full feature drivers are DALI

More information

Classification. 1 o Semestre 2007/2008

Classification. 1 o Semestre 2007/2008 Classification Departamento de Engenharia Informática Instituto Superior Técnico 1 o Semestre 2007/2008 Slides baseados nos slides oficiais do livro Mining the Web c Soumen Chakrabarti. Outline 1 2 3 Single-Class

More information