Paper: Going Beyond AER: An Extensive Analysis Of Word Alignments And Their Impact On MT

ACL ID P06-1002
Title Going Beyond AER: An Extensive Analysis Of Word Alignments And Their Impact On MT
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2006
Authors

This paper presents an extensive evalua- tion of five different alignments and in- vestigates their impact on the correspond- ing 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.