Machine Translation: From Research to Real Users: 5th Conference of the Association for Machine Translation in the Americas, AMTA 2002 Tiburon, CA, USA, October 8 – 12, 2002 Proceedings

AMTA 2002: From Research to Real Users Ever since the showdown between Empiricists and Rationalists a decade ago at TMI 92, MT researchers have hotly pursued promising paradigms for MT, including da- driven approaches (e.g., statistical, example-based) and hybrids that integrate these with more traditional rule-based components. During the same period, commercial MT systems with standard transfer archit- tures have evolved along a parallel and almost unrelated track, increasing their cov- age (primarily through manual update of their lexicons, we assume) and achieving much broader acceptance and usage, principally through the medium of the Internet. Webpage translators have become commonplace; a number of online translation s- vices have appeared, including in their offerings both raw and postedited MT; and large corporations have been turning increasingly to MT to address the exigencies of global communication. Still, the output of the transfer-based systems employed in this expansion represents but a small drop in the ever-growing translation marketplace bucket. Automatic Rule Learning for Resource-Limited MT....Pages 1-10 Toward a Hybrid Integrated Translation Environment....Pages 11-20 Adaptive Bilingual Sentence Alignment....Pages 21-30 DUSTer: A Method for Unraveling Cross-Language Divergences for Statistical Word-Level Alignment....Pages 31-43 Text Prediction with Fuzzy Alignments....Pages 44-53 Efficient Integration of Maximum Entropy Lexicon Models within the Training of Statistical Alignment Models....Pages 54-63 Using Word Formation Rules to Extend MT Lexicons....Pages 64-73 Example-Based Machine Translation via the Web....Pages 74-83 Handling Translation Divergences: Combining Statistical and Symbolic Techniques in Generation-Heavy Machine Translation....Pages 84-93 Korean-Chinese Machine Translation Based on Verb Patterns....Pages 94-103 Merging Example-Based and Statistical Machine Translation: An Experiment....Pages 104-113 Classification Approach to Word Selection in Machine Translation....Pages 114-123 Better Contextual Translation Using Machine Learning....Pages 124-134 Fast and Accurate Sentence Alignment of Bilingual Corpora....Pages 135-144 Deriving Semantic Knowledge from Descriptive Texts Using an MT System....Pages 145-154 Using a Large Monolingual Corpus to Improve Translation Accuracy....Pages 155-164 Semi-automatic Compilation of Bilingual Lexicon Entries from Cross-Lingually Relevant News Articles on WWW News Sites....Pages 165-176 Bootstrapping the Lexicon Building Process for Machine Translation between ‘New’ Languages....Pages 177-186 A Report on the Experiences of Implementing an MT System for Use in a Commercial Environment....Pages 187-194 Getting the Message In: A Global Company’s Experience with the New Generation of Low-Cost, High Performance Machine Translation Systems....Pages 195-206 An Assessment of Machine Translation for Vehicle Assembly Process Planning at Ford Motor Company....Pages 207-215 Fluent Machines’ EliMT System....Pages 216-219 LogoMedia TRANSLATETM, Version 2.0....Pages 220-223 Natural Intelligence in a Machine Translation System....Pages 224-228 Translation by the Numbers: Language Weaver....Pages 229-231 A New Family of the PARS Translation Systems....Pages 232-236 MSR-MT: The Microsoft Research Machine Translation System....Pages 237-239 The NESPOLE! Speech-to-Speech Translation System....Pages 240-243 The KANTOO MT System: Controlled Language Checker and Lexical Maintenance Tool....Pages 244-247 Approaches to Spoken Translation....Pages 248-252 This book constitutes the refereed proceedings of the 5th Conference of the Association for Machine Translation in the Americas, AMTA 2002, held in Tiburon, CA, USA, in October 2002. The 18 revised full technical papers, 3 user studies, and 9 system descriptions presented were carefully reviewed and selected for inclusion in the book. Among the issues addressed are hybrid translation environments, resource-limited MT, statistical word-level alignment, word formation rules, rule learning, web-based MT, translation divergences, example-based MT, data-driven MT, classification, contextual translation, the lexicon building process, commercial MT systems, speeck-to-speech translation, and language checking systems Machine Translation (MT) for minority languages offers significant potential benefits, but also presents serious scientific and economic challenges.