Lessons from NRC's Portage System at WMT 2010
نویسندگان
چکیده
NRC’s Portage system participated in the English-French (E-F) and French-English (F-E) translation tasks of the ACL WMT 2010 evaluation. The most notable improvement over earlier versions of Portage is an efficient implementation of lattice MERT. While Portage has typically performed well in Chinese to English MT evaluations, most recently in the NIST09 evaluation, our participation in WMT 2010 revealed some interesting differences between Chinese-English and E-F/F-E translation, and alerted us to certain weak spots in our system. Most of this paper discusses the problems we found in our system and ways of fixing them. We learned several lessons that we think will be of general interest.
منابع مشابه
NRC's PORTAGE System for WMT 2007
We present the PORTAGE statistical machine translation system which participated in the shared task of the ACL 2007 Second Workshop on Statistical Machine Translation. The focus of this description is on improvements which were incorporated into the system over the last year. These include adapted language models, phrase table pruning, an IBM1-based decoder feature, and rescoring with posterior...
متن کاملPORTAGE: with Smoothed Phrase Tables and Segment Choice Models
Improvements to Portage and its participation in the shared task of NAACL 2006 Workshop on Statistical Machine Translation are described. Promising ideas in phrase table smoothing and global distortion using feature-rich models are discussed as well as numerous improvements in the software base.
متن کاملMANY: Open Source MT System Combination at WMT'10
LIUM participated in the System Combination task of the Fifth Workshop on Statistical Machine Translation (WMT 2010). Hypotheses from 5 French/English MT systems were combined with MANY, an open source system combination software based on confusion networks currently developed at LIUM. The system combination yielded significant improvements in BLEU score when applied on WMT'09 data. The same be...
متن کاملPortage : Path Dependence and Increasing Returns in U . S . History ∗
We examine portage sites in the U.S. South, Mid-Atlantic, and Midwest, including those on the fall line, a geomorphologic feature in the southeastern U.S. marking the final rapids on rivers before the ocean. Historically, waterborne transport of goods required portage around the falls at these points, while some falls provided water power during early industrialization. These factors attracted ...
متن کاملCMU System Combination via Hypothesis Selection for WMT'10
This paper describes the CMU entry for the system combination shared task at WMT’10. Our combination method is hypothesis selection, which uses information from n-best lists from the input MT systems, where available. The sentence level features used are independent from the MT systems involved. Compared to the baseline we added source-to-target word alignment based features and trained system ...
متن کامل