Computer Science 577

Seminar in AI: Statistical Machine Translation

Spring 2004

Instructor: Dan Gildea
Location: TTh 5:00-6:15pm, CSB 703.

We'll discuss various statistical approaches to machine translation, examining different types of probabilistic models as well as the algorithms used for parameter estimation and decoding. Emphasis will be placed on how models handle specific linguistic phenomena and language pairs.

Homework 1

Syllabus

Introduction

Automating Knowledge Acquisition for Machine Translation, Kevin Knight. AI Magazine, 18(4), 1997.

Word-for-Word Translation

The Mathematics of Statistical Machine Translation: Parameter estimation, Peter F. Brown, Stephen A. Della Pietra, Vincent J. Della Pietra, and Robert L. Mercer. Computational Linguistics, 19(2):263-311, 1993.

Decoding Complexity in Word-Replacement Translation Models, Kevin Knight. Computational Linguistics, 25(4), 1999.

Word Reordering and a Dynamic Programming Beam Search Algorithm for Statistical Machine Translation, Christoph Tillmann and Hermann Ney. Computational Linguistics, 29:97-133, 2003.

A Maximum Entropy Approach to Natural Language Processing, Adam L. Berger, Vincent J. Della Pietra, and Stephen A. Della Pietra. Computational Linguistics, 22, 1996.

Phrase-based Systems

A Phrase-Based, Joint Probability Model for Statistical Machine Translation, Daniel Marcu and William Wong. In EMNLP-02, 2002.

Feature-Rich Statistical Translation of Noun Phrases, Philipp Koehn and Kevin Knight. In Proceedings of the 41th Annual Conference of the Association for Computational Linguistics (ACL-03), Sapporo, Japan, 2003.

Statistical Phrase-Based Translation, Philipp Koehn, Franz Josef Och, and Daniel Marcu. In Proceedings of the 2003 Meeting of the North American chapter of the Association for Computational Linguistics (NAACL-03), Edmonton, Alberta, 2003.

Syntax-Based Systems

Stochastic Inversion Transduction Grammars and Bilingual Parsing of Parallel Corpora, Dekai Wu. Computational Linguistics, 23(3):377-403, 1997.

A Comparative Study on Reordering Constraints in Statistical Machine Translation, Richard Zens and Hermann Ney. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Sapporo, Japan, 2003.

Machine Translation with a Stochastic Grammtical Channel, Dekai Wu and Hongsing Wong. In Proceedings of the 17th International Conference on Computational Linguistics (COLING/ACL-98), 1998.

A Syntax-Based Statistical Translation Model, Kenji Yamada and Kevin Knight. In Proceedings of the 39th Annual Conference of the Association for Computational Linguistics (ACL-01), Toulouse, France, 2001.

On the Complexity of ID/LP Parsing, G. Edward Barton, Jr. Computational Linguistics, 11(4):205-218, 1985.

Three Generative, Lexicalised Models for Statistical Parsing, Michael Collins. In Proceedings of the 35th Annual Conference of the Association for Computational Linguistics (ACL-97), pages 16-23, Madrid, Spain, 1997.

Language Modeling for MT 3/2

Immediate-Head Parsing for Language Models, Eugene Charniak. In Proceedings of the 39th Annual Conference of the Association for Computational Linguistics (ACL-01), Toulouse, France, 2001.

3/4

Syntax-based Language Models for Machine Translation, Eugene Charniak, Kevin Knight, and Kenji Yamada. In Proc. MT Summit IX, 2003.

Evaluation 3/16

Bleu: a method for automatic evaluation of machine translation, Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. In Proceedings of the 40th Annual Conference of the Association for Computational Linguistics (ACL-02), Philadelphia, PA, 2002.

Discriminative Training 3/18 11am

Discriminative training and maximum entropy models for statistical machine translation, Franz Josef Och and Hermann Ney. In Proceedings of the 40th Annual Conference of the Association for Computational Linguistics (ACL-02), Philadelphia, PA, 2002.

Minimum Error Rate Training for Statistical Machine Translation, Franz Josef Och. In Proceedings of the 41th Annual Conference of the Association for Computational Linguistics (ACL-03), 2003.

Synchronous Tree Adjoining Grammar 3/23

Synchronous Tree-Adjoining Grammars, Stuart Shieber and Yves Schabes. In Proceedings of the 13th International Conference on Computational Linguistics (COLING-90), pages 253-258, 1990.

3/25

A meta-level grammar: redefining synchronous TAG for translation and paraphrase, Mark Dras. In Proceedings of the 37th Annual Conference of the Association for Computational Linguistics (ACL-99), 1999.

Preserving semantic dependencies in synchronous tree adjoining grammar, William Schuler. In Proceedings of the 37th Annual Conference of the Association for Computational Linguistics (ACL-99), 1999.

Interlingua 4/1

Machine Translation Divergences: A Formal Description and Proposed Solution, Bonnie J. Dorr. Computational Linguistics, 20(4):597-633, 1994.

4/6

Knowledge-Based Machine Translation: the CMU Approach, Jaime Carbonell and Masaru Tomita. In Sergei Nirenburg, editor, Machine Translation: Theoretical and Methodological Issues, pages 68-89. Cambridge University Press, 1987. copies available in my office

4/8

Building a Large-Scale Knowledge Base for Machine Translation, Kevin Knight and Steve Luk. In Proc. of the National Conference on Artificial Intelligence (AAAI), 1994.

4/13

Controlled Language for Multilingual Machine Translation, Mitamura. In Proceedings of MT Summit, 1999.

4/15

Pronominal Anaphora Resolution in KANTOO Multilingual Machine Translation System, Teruko Mitamura, Eric Nyberg, Enrique Torrejon, Dave Svoboda, Annelen Brunner, and Kathryn Baker. In Proceedings of TMI, 2002.

Example-Based MT Mon 4/19 3:30pm

Experiments and Prospects Of Example-Based Machine Translation, Eiichiro Sumita and Hitoshi Iida. In 29th Annual Meeting of the Association for Computational Linguistics, 1991.

Example-Based Machine Translation in the Pangloss System, Ralf D. Brown. In Proceedings of the 16th International Conference on Computational Linguistics (COLING-96), 1996.

Multilingual NLP 4/20

Inducing Multilingual POS Taggers and NP Bracketers via Robust Projection across Aligned Corpora, David Yarowsky and Grace Ngai. In Proceedings of the 2001 Meeting of the North American chapter of the Association for Computational Linguistics (NAACL-01), pages 200-207, 2001.

Evaluating Translational Correspondence using Annotation Projection, Rebecca Hwa, Philip Resnik, Amy Weinberg, and Okan Kolak. In Proceedings of the 40th Annual Conference of the Association for Computational Linguistics (ACL-02), 2002.

4/22

The Web as a Parallel Corpus, Technical Report UMIACS-TR-2002-61, University of Maryland, 2002.

Tree Transducers 4/27

Training Tree Transducers, Jonathan Graehl and Kevin Knight. In Proceedings of the 2004 Meeting of the North American chapter of the Association for Computational Linguistics (NAACL-04), 2004.


gildea @ cs rochester edu
May 14, 2004