Why initialization matters for IBM model 1: multiple optima and non-strict convexity
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
Automatic projection of semantic structures: an application to pairwise translation ranking
SSST-5 Proceedings of the Fifth Workshop on Syntax, Semantics and Structure in Statistical Translation
Instance selection for machine translation using feature decay algorithms
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
Re-examining machine translation metrics for paraphrase identification
NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Head finalization reordering for Chinese-to-Japanese machine translation
SSST-6 '12 Proceedings of the Sixth Workshop on Syntax, Semantics and Structure in Statistical Translation
Hi-index | 0.00 |
The Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR (WMT10) took place on July 15 and 16 in Uppsala, Sweden, immediately following the 48th conference of the Association for Computational Linguistics (ACL). This is the sixth time this workshop has been held. The first time was in 2005 as part of the ACL 2005 Workshop on Building and Using Parallel Texts. In the following years the Workshop on Statistical Machine Translation was held at HLT-NAACL 2006 in New York City, USA, at ACL 2007 in Prague, Czech Republic, at ACL 2008 in Columbus, Ohio, USA, and at EACL 2009 in Athens, Greece. MetricsMATR was previously held in conjunction with AMTA 2008 in Honolulu, Hawaii, USA. The focus of our workshop was to evaluate the state of the art in machine translation for a variety of languages. Recent experimentation has shown that the performance of machine translation systems varies greatly with the source language. In this workshop we encouraged researchers to investigate ways to improve the performance of machine translation systems for diverse languages. Prior to the workshop, in addition to soliciting relevant papers for review and possible presentation we conducted a shared task that brought together machine translation systems for an evaluation on previously unseen data. The shared task also included a track for evaluation metrics and system combination methods. The results of the shared task were announced at the workshop, and these proceedings also include an overview paper that summarizes the results, as well as provides information about the data used and any procedures that were followed in conducting or scoring the task. In addition, there are short papers from each participating team that describe their underlying system in some detail. Like in previous years, we have received a far larger number of submission than we could accept for presentation. This year we have received 24 full paper submissions. 15 full papers were selected for oral presentation and one for poster presentation. We received 7 short paper submissions for the evaluation task, 9 short paper submissions for the system combination task, and 30 short paper submissions for the translation task. Due to the large number of high quality submission for the full paper track, shared task submissions were presented as posters. The poster session gave participants of the shared task the opportunity to present their approaches. The invited talk was given by Hermann Ney (RWTH Aachen).