2. Tree-to-String [6] (Phrase Based Machine Translation, PBMT)[1] [2] [7] (Targeted Self-Training) [7] Tree-to-String [3] Tree-to-String [4]
|
|
- Meghan Aileen George
- 5 years ago
- Views:
Transcription
1 1,a) 1,b) Graham Nubig 1,c) 1,d) 1,) 1. (Phras Basd Machin Translation, PBMT)[1] [2] Tr-to-String [3] Tr-to-String [4] [5] 1 Graduat School of Information Scinc, Nara Institut of Scinc and Tchnology a) morishita.makoto.mb1@is.naist.jp b) akab.koichi.zx8@is.naist.jp c) nubig@is.naist.jp d) koichiro@is.naist.jp ) s-nakamura@is.naist.jp [6] [7] (Targtd Slf-Training) [7] Tr-to-String 2. Tr-to-String f P r( f) ê c 2015 Information Procssing Socity of Japan 1
2 x 0 : P 1 P P x 1 : P x 0 saw a x 1 P ê := argmax P r( f) (1) Tr-to-String T f 2 Tr-to-String ê := argmax P r( f) = argmax P r( f, T f )P r(t f f) (2) T f argmax P r( T f )P r(t f f) (3) T f argmax P r( ˆT f ) (4) ˆT f ˆT f = argmax T f P r(t f f) (5) Tr-to-String 1 x 1 x 0, x 1 n n-bst Tr-to-String (Hypr-Graph) Forst-to-String [8] [9]Forst-to-String ê, ˆT f = arg max,t f P r( T f )P r(t f f) (6) (5) ˆ T f Charniak WSJ [10] (Probabilistic Contxt-Fr Grammar, PCFG) [11] PCFG-LA (PCFG with Latnt Annotations) [12]PCFG-LA EM PCFG-LA 3.2 Katz-Brown [13] [7] T f f rord(t f ) f scor(f, f ) ˆT f T f ˆT f = arg max T f T f scor(f, rord(t f )) (7) Tr-to-String [6] Tr-to-String 1-bst Tr-to-String c 2015 Information Procssing Socity of Japan 2
3 Katz-Brown [7] 1-bst Oracl bst 2 1-bst 1-bst (6) ˆT f bst 1-bst 1-bst n-bst E Oracl ē rror( ) ē = argmin E rror(, ) (8) n-bst Oracl Oracl 1-bst n-bst 1-bst Oracl Oracl Tr-to-String t i Oracl ē (i) Oracl E scor() {i scor(ē (i) ) t, ē (i) E} (9) 1-bst Oracl 1-bst Oracl Oracl 1-bst 1-bst ê (i) Oracl ē (i) c 2015 Information Procssing Socity of Japan 3
4 gain(ē (i), ê (i) ) = scor(ē (i) ) scor(ê (i) ) (10) (9) Gascó [14] N( + f ) f f + f N p( + f ) = N( + f ) N (11) ASPEC *1 WAT2014[15] Nubig [16] *2 Travatar[17] Forst-to-String PCFG-LA Egrt *3 JDC[18]( 7000 ) Egrt BLEU[19]RIBES[20] 2 BLEU+1[21] JDC ASPEC JDC [22] Parsr 1-bst (5) Egrt 1-bst MT 1-bst Egrt Travatar Travatar 1-bst *1 *2 *3 Oracl MT 1-bst Travatar 500-bst BLEU+1 n-bst Oracl (BLEU+1 t) Oracl BLEU+1 BLEU+1 Gain Oracl (BLEU+1 t) 1-bst Oracl BLEU+1 1/20 1/10 BLEU+1 Gain ( : p < 0.05, : p < 0.01) 1 (b),(c),(d) Egrt Sntncs JDC [6] Parsr 1-bst ( 1(b)) MT 1-bst Parsr 1-bst ( 1(c)) Oracl MT 1-bst ( 1(d)) BLEU+1 2 x c 2015 Information Procssing Socity of Japan 4
5 1 Sntnc slction Tr slction Sntncs (k) BLEU RIBES (a) Baslin (b) Parsr 1-bst Random Parsr 1-bst (c) MT 1-bst Random MT 1-bst (d) Oracl Random BLEU+1 1-bst () Oracl (BLEU+1 0.7) BLEU BLEU+1 1-bst (f) Oracl (BLEU+1 0.8) BLEU BLEU+1 1-bst (g) Oracl (BLEU+1 0.9) BLEU BLEU+1 1-bst (h) BLEU+1 Gain BLEU+1 Gain BLEU+1 1-bst Sntnc slction Tr slction Sntncs (k) BLEU RIBES (a) Baslin (b) Oracl Random BLEU+1 1-bst (c) Oracl (BLEU+1 0.8) BLEU BLEU+1 1-bst (d) Oracl (BLEU+1 0.9) BLEU BLEU+1 1-bst () BLEU+1 Gain BLEU+1 Gain BLEU+1 1-bst (f) Oracl (BLEU+1 0.8, Ja-En) BLEU BLEU+1 1-bst Sntncs 25k 20k 15k 10k 5k BLEU+1 Scor 2 Oracl BLEU+1 x x BLEU+1 Oracl BLEU+1 BLEU+1 ( 1(),(f),(g)) BLEU+1 MT 1-bst Oracl BLEU+1 BLEU+1 ( 1(h)) Tr-to-String 6. Tr-to-String 2 c 2015 Information Procssing Socity of Japan 5
6 3 Sourc Rfrnc in th C - administrd group, thrmal raction clarly incrasd th activity of R for 240 minuts. Baslin for 240 minuts clarly nhancd th activity of C administration group R. Oracl (BLEU+1 0.8) for 240 minuts clarly nhancd th activity of R in th C - administration group. P P P P P P P P P P P P P P P P P C P R C R (b) (a) 3 JSPS [1] Kohn, P., Och, F. J. and Marcu, D.: Statistical phrasbasd translation, Proc. HLT, pp (2003). [2] Yamada, K. and Knight, K.: A syntax-basd statistical translation modl, Proc. ACL (2001). [3] Liu, Y., Liu, Q. and Lin, S.: Tr-to-String Alignmnt Tmplat for Statistical Machin Translation, Proc. ACL (2006). [4] Nubig, G. and Duh, K.: On th Elmnts of an Accurat Tr-to-String Machin Translation Systm, Proc. ACL, pp (2014). [5] McClosky, D., Charniak, E. and Johnson, M.: Effctiv slf-training for parsing, Proc. HLT-NAACL, pp (2006). [6] Nubig, G.Sakti, S. Tr-to-String 21 (2015). [7] Katz-Brown, J., Ptrov, S., McDonald, R., Och, F., Talbot, D., Ichikawa, H., Sno, M. and Kazawa, H.: Training a Parsr for Machin Translation Rordring, Proc. EMNLP, pp (2011). [8] Mi, H., Huang, L. and Liu, Q.: Forst-Basd Translation, Proc. ACL, pp (2008). [9] Zhang, H. and Chiang, D.: An Exploration of Forstto-String Translation: Dos Translation Hlp or Hurt Parsing?, Proc. ACL, pp (2012). [10] Marcus, M. P., Marcinkiwicz, M. A. and Santorini, B.: Building a larg annotatd corpus of English: Th Pnn Trbank, Computational linguistics, Vol. 19, No. 2, pp (1993). [11] Charniak, E.: Statistical Parsing with a Contxt-Fr Grammar and Word Statistics, Proc. AAAI, pp (1997). [12] Huang, Z. and Harpr, M.: Slf-Training PCFG grammars with latnt annotations across languags, Proc. EMNLP, pp (2009). [13] Xia, F. and McCord, M.: Improving a statistical MT systm with automatically larnd rwrit pattrns, Proc. COLING (2004). [14] Gascó, G., Rocha, M.-A., Sanchis-Trills, G., Andrés- Frrr, J. and Casacubrta, F.: Dos mor data always yild bttr translations?, Proc. ACL, pp (2012). [15] Nakazawa, T., Mino, H., Goto, I., Kurohashi, S. and Sumita, E.: Ovrviw of th 1st Workshop on Asian Translation, Proc. WAT (2014). [16] Nubig, G.: Forst-to-String SMT for Asian Languag Translation: NAIST at WAT2014, Proc. WAT (2014). [17] Nubig, G.: Travatar: A Forst-to-String Machin Translation Engin basd on Tr Transducrs, Proc. ACL Dmo Track, pp (2013). [18] Mori, S., Ogura, H. and Sasada, T.: A Japans Word Dpndncy Corpus, Proc. LREC (2014). [19] Papinni, K., Roukos, S., Ward, T. and Zhu, W.-J.: BLEU: a mthod for automatic valuation of machin translation, Proc. ACL, pp (2002). [20] Isozaki, H., Hirao, T., Duh, K., Sudoh, K. and Tsukada, c 2015 Information Procssing Socity of Japan 6
7 H.: Automatic Evaluation of Translation Quality for Distant Languag Pairs, Proc. EMNLP, pp (2010). [21] Lin, C.-Y. and Och, F. J.: Orang: a mthod for valuating automatic valuation mtrics for machin translation, Proc. COLING, pp (2004). [22] Kohn, P.: Statistical significanc tsts for machin translation valuation, Proc. EMNLP (2004). c 2015 Information Procssing Socity of Japan 7
Shift-Reduce Word Reordering for Machine Translation
Shift-Reduce Word Reordering for Machine Translation Katsuhiko Hayashi, Katsuhito Sudoh, Hajime Tsukada, Jun Suzuki, Masaaki Nagata NTT Communication Science Laboratories, NTT Corporation 2-4 Hikaridai,
More informationShift-Reduce Word Reordering for Machine Translation
Shift-Reduce Word Reordering for Machine Translation Katsuhiko Hayashi, Katsuhito Sudoh, Hajime Tsukada, Jun Suzuki, Masaaki Nagata NTT Communication Science Laboratories, NTT Corporation 2-4 Hikaridai,
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 informationImproving Decoding Generalization for Tree-to-String Translation
Improving Dcoding Gnralization for Tr-to-String Translation Jingbo Zhu Natural Languag Procssing Laboratory Northastrn Univrsity, Shnyang, China zhujingbo@mail.nu.du.cn Tong Xiao Natural Languag Procssing
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 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 informationORANGE: a Method for Evaluating Automatic Evaluation Metrics for Machine Translation
ORANGE: a Method for Evaluating Automatic Evaluation Metrics for Machine Translation Chin-Yew Lin and Franz Josef Och Information Sciences Institute University of Southern California 4676 Admiralty Way
More informationLecture 9: Decoding. Andreas Maletti. Stuttgart January 20, Statistical Machine Translation. SMT VIII A. Maletti 1
Lecture 9: Decoding Andreas Maletti Statistical Machine Translation Stuttgart January 20, 2012 SMT VIII A. Maletti 1 Lecture 9 Last time Synchronous grammars (tree transducers) Rule extraction Weight training
More informationUtilizing Portion of Patent Families with No Parallel Sentences Extracted in Estimating Translation of Technical Terms
1 1 1 2 2 30% 70% 70% NTCIR-7 13% 90% 1,000 Utilizing Portion of Patent Families with No Parallel Sentences Extracted in Estimating Translation of Technical Terms Itsuki Toyota 1 Yusuke Takahashi 1 Kensaku
More informationImproving Sequence-to-Sequence Constituency Parsing
Improving Sequence-to-Sequence Constituency Parsing Lemao Liu, Muhua Zhu and Shuming Shi Tencent AI Lab, Shenzhen, China {redmondliu,muhuazhu, shumingshi}@tencent.com Abstract Sequence-to-sequence constituency
More informationInvestigating Connectivity and Consistency Criteria for Phrase Pair Extraction in Statistical Machine Translation
Investigating Connectivity and Consistency Criteria for Phrase Pair Extraction in Statistical Machine Translation Spyros Martzoukos Christophe Costa Florêncio and Christof Monz Intelligent Systems Lab
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 informationTree as a Pivot: Syntactic Matching Methods in Pivot Translation
Tree as a Pivot: Syntactic Matching Methods in Pivot Translation Akiva Miura, Graham Neubig,, Katsuhito Sudoh, Satoshi Nakamura Nara Institute of Science and Technology, Japan Carnegie Mellon University,
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 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 informationNatural Language Processing (CSEP 517): Machine Translation (Continued), Summarization, & Finale
Natural Language Processing (CSEP 517): Machine Translation (Continued), Summarization, & Finale Noah Smith c 2017 University of Washington nasmith@cs.washington.edu May 22, 2017 1 / 30 To-Do List Online
More informationA Deterministic Word Dependency Analyzer Enhanced With Preference Learning
A Deterministic Word Dependency Analyzer Enhanced With Preference Learning Hideki Isozaki and Hideto Kazawa and Tsutomu Hirao NTT Communication Science Laboratories NTT Corporation 2-4 Hikaridai, Seikacho,
More informationAutomatically Evaluating Text Coherence using Anaphora and Coreference Resolution
1 1 Barzilay 1) Automatically Evaluating Text Coherence using Anaphora and Coreference Resolution Ryu Iida 1 and Takenobu Tokunaga 1 We propose a metric for automatically evaluating discourse coherence
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 informationMaschinelle Sprachverarbeitung
Maschinelle Sprachverarbeitung Parsing with Probabilistic Context-Free Grammar Ulf Leser Content of this Lecture Phrase-Structure Parse Trees Probabilistic Context-Free Grammars Parsing with PCFG Other
More informationMaschinelle Sprachverarbeitung
Maschinelle Sprachverarbeitung Parsing with Probabilistic Context-Free Grammar Ulf Leser Content of this Lecture Phrase-Structure Parse Trees Probabilistic Context-Free Grammars Parsing with PCFG Other
More informationBetter Learning and Decoding for Syntax Based SMT Using PSDIG
Bttr Larning and Dcoding or Syntax Basd SMT Using PSDIG Yuan Ding Martha Palmr Dpartmnt o Computr and Inormation Scinc Univrsity o Pnnsylvania Philadlphia, PA 19104, USA {yding, mpalmr}@cis.upnn.du Abstract
More informationFourth-Order Dependency Parsing
Fourth-Order Dependency Parsing X uezhe Ma 1,2 Hai Zhao 1,2 (1) Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering, Shanghai Jiao Tong University (2)
More 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 informationMulti-Metric Optimization Using Ensemble Tuning
Multi-Metric Optimization Using Ensemble Tuning Baskaran Sankaran, Anoop Sarkar Simon Fraser University Burnaby BC. CANADA {baskaran,anoop}@cs.sfu.ca Kevin Duh Nara Institute of Science & Technology Ikoma,
More informationMarrying Dynamic Programming with Recurrent Neural Networks
Marrying Dynamic Programming with Recurrent Neural Networks I eat sushi with tuna from Japan Liang Huang Oregon State University Structured Prediction Workshop, EMNLP 2017, Copenhagen, Denmark Marrying
More informationFast Consensus Decoding over Translation Forests
Fast Consensus Decoding over Translation Forests John DeNero Computer Science Division University of California, Berkeley denero@cs.berkeley.edu David Chiang and Kevin Knight Information Sciences Institute
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 informationStatistical Machine Translation of Natural Languages
1/26 Statistical Machine Translation of Natural Languages Heiko Vogler Technische Universität Dresden Germany Graduiertenkolleg Quantitative Logics and Automata Dresden, November, 2012 1/26 Weighted Tree
More informationComputing Lattice BLEU Oracle Scores for Machine Translation
Computing Lattice Oracle Scores for Machine Translation Artem Sokolov & Guillaume Wisniewski & François Yvon {firstname.lastname}@limsi.fr LIMSI, Orsay, France 1 Introduction 2 Oracle Decoding Task 3 Proposed
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 informationStatistical Machine Translation of Natural Languages
1/37 Statistical Machine Translation of Natural Languages Rule Extraction and Training Probabilities Matthias Büchse, Toni Dietze, Johannes Osterholzer, Torsten Stüber, Heiko Vogler Technische Universität
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 informationImproving Relative-Entropy Pruning using Statistical Significance
Improving Relative-Entropy Pruning using Statistical Significance Wang Ling 1,2 N adi Tomeh 3 Guang X iang 1 Alan Black 1 Isabel Trancoso 2 (1)Language Technologies Institute, Carnegie Mellon University,
More informationFeature-Rich Translation by Quasi-Synchronous Lattice Parsing
Feature-Rich Translation by Quasi-Synchronous Lattice Parsing Kevin Gimpel and Noah A. Smith Language Technologies Institute School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213,
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 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 informationMachine Translation without Words through Substring Alignment
Machine Translation without Words through Substring Alignment Graham Neubig 1,2,3, Taro Watanabe 2, Shinsuke Mori 1, Tatsuya Kawahara 1 1 2 3 now at 1 Machine Translation Translate a source sentence F
More informationTheory of Alignment Generators and Applications to Statistical Machine Translation
Theory of Alignment Generators and Applications to Statistical Machine Translation Hemanta K Maji Raghavendra Udupa U IBM India Research Laboratory, New Delhi {hemantkm, uraghave}@inibmcom Abstract Viterbi
More informationMulti-Task Word Alignment Triangulation for Low-Resource Languages
Multi-Task Word Alignment Triangulation for Low-Resource Languages Tomer Levinboim and David Chiang Department of Computer Science and Engineering University of Notre Dame {levinboim.1,dchiang}@nd.edu
More informationTensor Decomposition for Fast Parsing with Latent-Variable PCFGs
Tensor Decomposition for Fast Parsing with Latent-Variable PCFGs Shay B. Cohen and Michael Collins Department of Computer Science Columbia University New York, NY 10027 scohen,mcollins@cs.columbia.edu
More informationUsing a Mixture of N-Best Lists from Multiple MT Systems in Rank-Sum-Based Confidence Measure for MT Outputs
Using a Mixture of N-Best Lists from Multiple MT Systems in Rank-Sum-Based Confidence Measure for MT Outputs Yasuhiro Akiba,, Eiichiro Sumita, Hiromi Nakaiwa, Seiichi Yamamoto, and Hiroshi G. Okuno ATR
More informationMulti-Source Neural Translation
Multi-Source Neural Translation Barret Zoph and Kevin Knight Information Sciences Institute Department of Computer Science University of Southern California {zoph,knight}@isi.edu Abstract We build a multi-source
More informationarxiv: v1 [cs.cl] 12 Dec 2016
Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices Felix Stahlberg and Adrià de Gispert and Eva Hasler and Bill Byrne Department of Engineering, University
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 informationHow to train your multi bottom-up tree transducer
How to train your multi bottom-up tree transducer Andreas Maletti Universität tuttgart Institute for Natural Language Processing tuttgart, Germany andreas.maletti@ims.uni-stuttgart.de Portland, OR June
More informationProbabilistic Context-Free Grammar
Probabilistic Context-Free Grammar Petr Horáček, Eva Zámečníková and Ivana Burgetová Department of Information Systems Faculty of Information Technology Brno University of Technology Božetěchova 2, 612
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 informationThe Infinite PCFG using Hierarchical Dirichlet Processes
S NP VP NP PRP VP VBD NP NP DT NN PRP she VBD heard DT the NN noise S NP VP NP PRP VP VBD NP NP DT NN PRP she VBD heard DT the NN noise S NP VP NP PRP VP VBD NP NP DT NN PRP she VBD heard DT the NN noise
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 informationWhy Synchronous Tree Substitution Grammars?
Why ynchronous Tr ustitution Grammars? Andras Maltti Univrsitat Rovira i Virgili Tarragona, pain andras.maltti@urv.cat Los Angls Jun 4, 2010 Why ynchronous Tr ustitution Grammars? A. Maltti 1 Motivation
More informationPhrase Table Pruning via Submodular Function Maximization
Phrase Table Pruning via Submodular Function Maximization Masaaki Nishino and Jun Suzuki and Masaaki Nagata NTT Communication Science Laboratories, NTT Corporation 2-4 Hikaridai, Seika-cho, Soraku-gun,
More informationMinimum Error Rate Training Semiring
Minimum Error Rate Training Semiring Artem Sokolov & François Yvon LIMSI-CNRS & LIMSI-CNRS/Univ. Paris Sud {artem.sokolov,francois.yvon}@limsi.fr EAMT 2011 31 May 2011 Artem Sokolov & François Yvon (LIMSI)
More informationBayesian Learning of Non-compositional Phrases with Synchronous Parsing
Bayesian Learning of Non-compositional Phrases with Synchronous Parsing Hao Zhang Computer Science Department University of Rochester Rochester, NY 14627 zhanghao@cs.rochester.edu Chris Quirk Microsoft
More informationMulti-Source Neural Translation
Multi-Source Neural Translation Barret Zoph and Kevin Knight Information Sciences Institute Department of Computer Science University of Southern California {zoph,knight}@isi.edu In the neural encoder-decoder
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 informationToponym Disambiguation in an English-Lithuanian SMT System with Spatial Knowledge
Toponym Disambiguation in an English-Lithuanian SMT System with Spatial Knowledge Raivis Skadiņš Tilde SIA Vienibas gatve 75a, Riga, Latvia raiviss@tilde.lv Tatiana Gornostay Tilde SIA Vienibas gatve 75a,
More informationMinimum Bayes-risk System Combination
Minimum Bayes-risk System Combination Jesús González-Rubio Instituto Tecnológico de Informática U. Politècnica de València 46022 Valencia, Spain jegonzalez@iti.upv.es Alfons Juan Francisco Casacuberta
More information{Probabilistic Stochastic} Context-Free Grammars (PCFGs)
{Probabilistic Stochastic} Context-Free Grammars (PCFGs) 116 The velocity of the seismic waves rises to... S NP sg VP sg DT NN PP risesto... The velocity IN NP pl of the seismic waves 117 PCFGs APCFGGconsists
More informationTriplet 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 informationAutomatic Evaluation of Machine Translation Quality Using Longest Common Subsequence and Skip-Bigram Statistics
Automatic Evaluation of Machine Translation Quality Using Longest Common Subsequence and Skip-Bigram Statistics Chin-Yew Lin and Franz Josef Och Information Sciences Institute University of Southern California
More informationCKY-based Convolutional Attention for Neural Machine Translation
CKY-based Convolutional Attention for Neural Machine Translation Taiki Watanabe and Akihiro Tamura and Takashi Ninomiya Ehime University 3 Bunkyo-cho, Matsuyama, Ehime, JAPAN {t_watanabe@ai.cs, tamura@cs,
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 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 informationSmoothing for Bracketing Induction
Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence Smoothing for racketing Induction Xiangyu Duan, Min Zhang *, Wenliang Chen Soochow University, China Institute
More informationLogistic Normal Priors for Unsupervised Probabilistic Grammar Induction
Logistic Normal Priors for Unsupervised Probabilistic Grammar Induction Shay B. Cohen Kevin Gimpel Noah A. Smith Language Technologies Institute School of Computer Science Carnegie Mellon University {scohen,gimpel,nasmith}@cs.cmu.edu
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 informationToponym Disambiguation using Ontology-based Semantic Similarity
Toponym Disambiguation using Ontology-based Semantic Similarity David S Batista 1, João D Ferreira 2, Francisco M Couto 2, and Mário J Silva 1 1 IST/INESC-ID Lisbon, Portugal {dsbatista,msilva}@inesc-id.pt
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 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 informationProbabilistic models for disambiguation of an HPSG-based chart generator
Probabilistic modls for disambiguation of an HPSG-basd chart gnrator Hiroko Nakanishi Yusuk Miyao Jun ichi Tsujii Dpartmnt of Computr Scinc CREST, JST School of Informatics Univrsity of Tokyo Hongo 7-3-1,
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 informationBayes Risk Minimization in Natural Language Parsing
UNIVERSITE DE GENEVE CENTRE UNIVERSITAIRE D INFORMATIQUE ARTIFICIAL INTELLIGENCE LABORATORY Date: June, 2006 TECHNICAL REPORT Baes Risk Minimization in Natural Language Parsing Ivan Titov Universit of
More informationProbabilistic Graphical Models: MRFs and CRFs. CSE628: Natural Language Processing Guest Lecturer: Veselin Stoyanov
Probabilistic Graphical Models: MRFs and CRFs CSE628: Natural Language Processing Guest Lecturer: Veselin Stoyanov Why PGMs? PGMs can model joint probabilities of many events. many techniques commonly
More informationAutomatic Evaluation in Text Summarization
1 Automatic Evaluation in Text Summarization Hidetsugu Nanba Tsutomu Hirao Hiroshima City University nanba@hiroshima-cuacjp, http://wwwnlpitshiroshima-cuacjp/~nanba/ NTT NTT Communication Science Laboratories
More informationCMU at SemEval-2016 Task 8: Graph-based AMR Parsing with Infinite Ramp Loss
CMU at SemEval-2016 Task 8: Graph-based AMR Parsing with Infinite Ramp Loss Jeffrey Flanigan Chris Dyer Noah A. Smith Jaime Carbonell School of Computer Science, Carnegie Mellon University, Pittsburgh,
More informationNatural Language Processing (CSE 517): Machine Translation
Natural Language Processing (CSE 517): Machine Translation Noah Smith c 2018 University of Washington nasmith@cs.washington.edu May 23, 2018 1 / 82 Evaluation Intuition: good translations are fluent in
More informationCreating Disjunctive Logical Forms from Aligned Sentences for Grammar-Based Paraphrase Generation
Crating Disjunctiv Logical Forms from Alignd Sntncs for Grammar-Basd Paraphras Gnration Scott Martin and Michal Whit Dpartmnt of Linguistics Th Ohio Stat Univrsity Columbus, Ohio, USA {scott,mwhit}@ling.ohio-stat.du
More informationPhrasetable Smoothing for Statistical Machine Translation
Phrasetable Smoothing for Statistical Machine Translation George Foster and Roland Kuhn and Howard Johnson National Research Council Canada Ottawa, Ontario, Canada firstname.lastname@nrc.gc.ca Abstract
More informationWord Alignment by Thresholded Two-Dimensional Normalization
Word Alignment by Thresholded Two-Dimensional Normalization Hamidreza Kobdani, Alexander Fraser, Hinrich Schütze Institute for Natural Language Processing University of Stuttgart Germany {kobdani,fraser}@ims.uni-stuttgart.de
More informationThe Research on Syntactic Features in Semantic Role Labeling
23 6 2009 11 J OU RNAL OF CH IN ESE IN FORMA TION PROCESSIN G Vol. 23, No. 6 Nov., 2009 : 100320077 (2009) 0620011208,,,, (, 215006) :,,,( NULL ),,,; CoNLL22005 Shared Task WSJ 77. 54 %78. 75 %F1, : ;;;;
More informationMaximal Lattice Overlap in Example-Based Machine Translation
Maximal Lattice Overlap in Example-Based Machine Translation Rebecca Hutchinson Paul N. Bennett Jaime Carbonell Peter Jansen Ralf Brown June 6, 2003 CMU-CS-03-138 School of Computer Science Carnegie Mellon
More informationTransition-Based Parsing
Transition-Based Parsing Based on atutorial at COLING-ACL, Sydney 2006 with Joakim Nivre Sandra Kübler, Markus Dickinson Indiana University E-mail: skuebler,md7@indiana.edu Transition-Based Parsing 1(11)
More informationProcessing/Speech, NLP and the Web
CS460/626 : Natural Language Processing/Speech, NLP and the Web (Lecture 25 Probabilistic Parsing) Pushpak Bhattacharyya CSE Dept., IIT Bombay 14 th March, 2011 Bracketed Structure: Treebank Corpus [ S1[
More informationPAPER Bayesian Word Alignment and Phrase Table Training for Statistical Machine Translation
1536 IEICE TRANS. INF. & SYST., VOL.E96 D, NO.7 JULY 2013 PAPER Bayesian Word Alignment and Phrase Table Training for Statistical Machine Translation Zezhong LI a, Member, Hideto IKEDA, Nonmember, and
More informationS NP VP 0.9 S VP 0.1 VP V NP 0.5 VP V 0.1 VP V PP 0.1 NP NP NP 0.1 NP NP PP 0.2 NP N 0.7 PP P NP 1.0 VP NP PP 1.0. N people 0.
/6/7 CS 6/CS: Natural Language Processing Instructor: Prof. Lu Wang College of Computer and Information Science Northeastern University Webpage: www.ccs.neu.edu/home/luwang The grammar: Binary, no epsilons,.9..5
More informationEfficient Incremental Decoding for Tree-to-String Translation
Efficient Incremental Decoding for Tree-to-String Translation Liang Huang 1 1 Information Sciences Institute University of Southern California 4676 Admiralty Way, Suite 1001 Marina del Rey, CA 90292, USA
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 informationIntegrating Morphology in Probabilistic Translation Models
Integrating Morphology in Probabilistic Translation Models Chris Dyer joint work with Jon Clark, Alon Lavie, and Noah Smith January 24, 2011 lti das alte Haus the old house mach das do that 2 das alte
More informationIntroduction to Probablistic Natural Language Processing
Introduction to Probablistic Natural Language Processing Alexis Nasr Laboratoire d Informatique Fondamentale de Marseille Natural Language Processing Use computers to process human languages Machine Translation
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 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 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 informationDynamic Programming for Linear-Time Incremental Parsing
Dynamic Programming for Linear-Time Incremental Parsing Liang Huang USC Information Sciences Institute 4676 Admiralty Way, Suite 1001 Marina del Rey, CA 90292 lhuang@isi.edu Kenji Sagae USC Institute for
More informationPenn Treebank Parsing. Advanced Topics in Language Processing Stephen Clark
Penn Treebank Parsing Advanced Topics in Language Processing Stephen Clark 1 The Penn Treebank 40,000 sentences of WSJ newspaper text annotated with phrasestructure trees The trees contain some predicate-argument
More 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 informationIntroduction to Data-Driven Dependency Parsing
Introduction to Data-Driven Dependency Parsing Introductory Course, ESSLLI 2007 Ryan McDonald 1 Joakim Nivre 2 1 Google Inc., New York, USA E-mail: ryanmcd@google.com 2 Uppsala University and Växjö University,
More 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 informationCross-Entropy and Estimation of Probabilistic Context-Free Grammars
Cross-Entropy and Estimation of Probabilistic Context-Free Grammars Anna Corazza Department of Physics University Federico II via Cinthia I-8026 Napoli, Italy corazza@na.infn.it Giorgio Satta Department
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 information