Labeled Alignment for Recognizing Textual Entailment
Xiaolin Wang, Hai Zhao, Bao‐Liang Lu · International Joint Conference on Natural Language Processing · 2013
Recognizing Textual Entailment (RTE) is to predict whether one text fragment can semantically infer another, which is required across multiple applications of natural language processing. The conventional alignment scheme, which is developed for machine translation, only marks the paraphrases and hyponyms to justify the entailment pairs, while provides less support for the non-entailment ones. This paper proposes a novel alignment scheme, named labeled alignment, to address this problem, which introduces negative links to explicitly mark the contradictory expressions to justify the non-entailment pairs. Thus the alignment-based RTE method employing the proposed scheme, compared with those employing the conventional one, can gain accuracy improvement through actively detecting the signals of non-entailment. The experimental results on the data sets of two shared RTE tasks indicate the implemented system significantly outperforms both the baseline system and all the other submitted systems.