TY - CONF T1 - Going beyond AER: an extensive analysis of word alignments and their impact on MT T2 - Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics Y1 - 2006 A1 - Ayan,Necip Fazil A1 - Dorr, Bonnie J AB - This paper presents an extensive evaluation of five different alignments and investigates their impact on the corresponding MT system output. We introduce new measures for intrinsic evaluations and examine the distribution of phrases and untranslated words during decoding to identify which characteristics of different alignments affect translation. We show that precision-oriented alignments yield better MT output (translating more words and using longer phrases) than recall-oriented alignments. JA - Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics T3 - ACL-44 PB - Association for Computational Linguistics CY - Stroudsburg, PA, USA UR - http://dx.doi.org/10.3115/1220175.1220177 M3 - 10.3115/1220175.1220177 ER -