Abstract
This paper presents a new approach to combining outputs of existing word alignment systems. Each alignment link is represented with a set of feature functions extracted from linguistic features and input alignments. These features are used as the basis of alignment decisions made by a maximum entropy approach. The learning method has been evaluated on three language pairs, yielding significant improvements over input alignments and three heuristic combination methods. The impact of word alignment on MT quality is investigated, using a phrase-based MT system. © 2006 Association for Computational Linguistics.
Cite
CITATION STYLE
Ayan, N. F., & Dorr, B. J. (2006). A maximum entropy approach to combining word alignments. In HLT-NAACL 2006 - Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings of the Main Conference (pp. 96–103). Association for Computational Linguistics (ACL). https://doi.org/10.3115/1220835.1220848
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
