AMTA 2006


Proceedings of the 7th Conference of the

Association for Machine Translation of the Americas


Visions for the Future of Machine Translation


August 8-12, 2006

Cambridge, Massachusetts, USA


Table of contents


Preface from the General Chair


Preface from the Program Chairs


Conference Organizers


Program Committee -- Reviewers


Guarani: A Case Study in Resource Development for Quick Ramp-Up MT -- Ahmed Abdelali, James Cowie, Steve Helmreich, Wanying Jin, Maria Pilar Milagros, Bill Ogden, and Mansouri Rad and Ron Zacharski; pp. 1-9


Constraining the Phrase-Based, Joint Probability Statistical Translation Model -- Alexandra Birch, Chris Callison-Burch and Miles Osborne; pp. 10-18


Context-Based Machine Translation --  Jaime Carbonell, Steve Klein, David Miller, Mike Steinbaum, Tomer Grassiany and Jochen Frei; pp. 19-28


Integration of POStag-based Source Reordering into SMT Decoding by an Extended Search Graph  -- Josep M.Crego and Josι B.Mariρo; pp. 29-36


Better Learning and Decoding for Syntax Based SMT Using PSDIG -- Yuan Ding and Martha Palmer; pp.37-45


The Added Value of Free Online MT Services: Confidence Boosters for Linguistically-challenged Internet Users, a Case Study for the Language Pair Italian-English --  Federico Gaspari; pp.46-55


Challenges in Building an Arabic-English GHMT System with SMT Components -- Nizar Habash, Bonnie Dorr and Christof Monz; pp. 56-65


Statistical Syntax-Directed Translation with Extended Domain of Locality -- Liang Huang, Kevin Knight and Aravind Joshi; pp. 66-73


Corpus Variations for Translation Lexicon Induction -- Rebecca Hwa, Carol Nichols and Khalil Sima'an; pp. 74-81


Toward an Interagency Language Roundtable Based Assessment of Speech-to-Speech Translation Capabilities -- Douglas Jones, Timothy Anderson, Sabine Atwell, Brian Delaney, James Dirgin, Michael Emots,Neil Granoein, Martha Herzog, Timothy Hunter, Sargon Jabri, Wade Shen and Jurgen Sottung; pp. 82-89


Word-Based Alignment, Phrase-Based Translation: What's the Link? -- Adam Lopez and Philip Resnik; pp. 90-99


Translation of Multiword Expressions Using Parallel Suffix Arrays -- Paul McNamee and James Mayfield; pp. 100-109


Multi-Engine Machine Translation by Recursive Sentence Decomposition -- Bart Mellebeek, Karolina Owczarzak, Josef Van Genabith and Andy Way; pp. 110-118


Toward Communicating Simple Sentences Using Pictorial Representations -- Rada Mihalcea and Ben Leong; pp. 119-127


Induction of Probabilistic Synchronous Tree-Insertion Grammars for Machine Translation -- Rebecca Nesson, Stuart Shieber and Alexander Rush; pp. 128-137


Improving Phrase-Based Statistical Machine Translation with Morpho-Syntactic Analysis and Transformation -- Thai Phuong Nguyen and Akira Shimazu; pp. 138-147


Wrapper Syntax for Example-based Machine Translation -- Karolina Owczarzak, Bart Mellebeek, Declan Groves, Josef Van Genabith and Andy Way; pp. 148-155


Machine Translation for Languages Lacking Bitext via Multilingual Gloss Transduction -- Brock Pytlik and David Yarowsky; pp. 156-165


Direct Application of a Language Learner Test to MT Evaluation -- Florence Reeder; pp. 166-175


Measuring MT Adequacy Using Latent Semantic Analysis -- Florence Reeder; pp. 176-184


Minimally Supervised Morphological Segmentation with Applications to Machine Translation -- Jason Riesa and David Yarowsky; pp. 185-192


Ambiguity Reduction for Machine Translation: Human-Computer Collaboration -- Marcus Sammer, Kobi Reiter, Stephen Soderland, Katrin Kirchhoff and Oren Etzioni; pp. 193-202


Novel Probabilistic Finite-State Transducers for Cognate and Transliteration Modeling -- Charles Schafer; pp. 203-212


Combining Linguistic and Statistical Methods for Bi-directional English Chinese Translation in the Flight Domain  -- Stephanie Seneff, Chao Wang and John Lee; pp. 213-222


A Study of Translation Edit Rate with Targeted Human Annotation -- Matthew Snover, Bonnie Dorr, Rich Schwartz, Linnea Micciulla and John Makhoul; pp. 223-231


Example-Based Machine Translation of the Basque Language -- Nicolas Stroppa, Declan Groves, Andy Way and Kepa Sarasola; pp. 232-241


Combining Evaluation Metrics via Loss Functions -- Calandra Tate and Clare Voss; pp. 242-250


Scalable Purely-Discriminative Training for Word and Tree Transducers -- Benjamin Wellington, Joseph Turian, Chris Pike and Dan Melamed; pp. 251-260


Invited talks


The Potential and Limitations of MT Paradigm – Daniel Marcu and Alan Melby (9 August 2006); expanded version with annotations added after the debate


Joseph Olive (Program Manager, DARPA) (10 August 2006)


User Track – presentations

9 August

Evaluating MT prior to deployment – Donald A. DePalma


Expecting the Unexpected: Using MT Operationally – Florence Reeder [not available]


The Added Value of Free Online MT Services – Federico Gaspari


Document and Media Exploitation Evaluation – Nick Bemish [not available]


GPHIN use of MT in disease outbreak detection – Michael Blench


Services Canada – Use of MT to translate online job listings – Michael Blench


10 August

Real-Time Closed Caption Translation – Mary Flanagan [not available]


Machine translation and translation memory:  a message of reconciliation – Jost Zetzsche


Lionbridge – Two case studies using MT in location – Rafa Moral [not available]




Machine translation for social impact  (9 August 2006):


            Description of panel, by Violetta Cavalli-Sforza


Meadan global dialogue – Ed Bice


                The social impact of online MT – Federico Gaspari


                Social impact of MT – Jennifer DeCamp


                MT for social impact – Michael McCord


                The social impact of translation via SMS – Rami B. Safadi


Hybrid machine translation (11 August 2006):


            Description of panel: Hybrid machine translation: why and how? – Violetta Cavalli-Sforza and Alon Lavie




                Presentation by Jaime Carbonell


                Presentation by Nizar Habash


                Statistical machine translation and hybrid machine translation – Philipp Koehn


                Combining interlingua with SMT – Stephanie Seneff


                First strategies for integrating hybrid approaches into established systems – Jean Senellart and John S. White


Tutorials (8 August 2006)


A Gentle Introduction to Ontologies – Eduard Hovy


Tools and Techniques for Translatable Content – Mike Dillinger


Arabic Dialect Processing – Mona Diab and Nizar Habash


An Overview of Statistical Machine Translation – David Smith and Charles Schafer


Name Translation – Keith Miller and Sherri Condon


Pre-conference Workshop (8 August 2006)


MT in Computer Assisted Translation and Language Learning [no materials available]


Post-conference Workshops (12 August 2006)


MT Evaluation: the Black Box in the Hall of Mirrors [no materials available]


Automated Postediting [no materials available]


CLAW 2006: 5th International Workshop on Controlled Language Applications (12 August 2006)