Paper: Exploiting Qualitative Information from Automatic Word Alignment for Cross-lingual NLP Tasks

ACL ID P13-2135
Title Exploiting Qualitative Information from Automatic Word Alignment for Cross-lingual NLP Tasks
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

The use of automatic word alignment to capture sentence-level semantic relations is common to a number of cross-lingual NLP applications. Despite its proved usefulness, however, word alignment in- formation is typically considered from a quantitative point of view (e.g. the number of alignments), disregarding qualitative aspects (the importance of aligned terms). In this paper we demonstrate that integrat- ing qualitative information can bring sig- nificant performance improvements with negligible impact on system complexity. Focusing on the cross-lingual textual en- tailment task, we contribute with a novel method that: i) significantly outperforms the state of the art, and ii) is portable, with limited loss in performance, to language pairs where training data are not available.