arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.07656cs.CL
收藏

利用自然演绎证明获取短语对应

Acquisition of Phrase Correspondences using Natural Deduction Proofs

The University of Tokyo(东京大学);Ochanomizu University(御茶水女子大学);Artificial Intelligence Research Center, AIST(产业技术综合研究所人工智能研究中心)

Hitomi Yanaka, Koji Mineshima, Pascual Martinez-Gomez, Daisuke Bekki

摘要:

如何识别、提取和使用短语知识是文本蕴涵识别的关键问题。为了解决这个问题,我们提出了一种方法来检测释义通过自然演绎证明句子对之间的语义关系。我们的解决方案依赖于部分变量统一的图形重构和一个算法,诱导子图之间的对齐的意义表示。实验表明,该方法可以自动检测出现有释义数据库中不存在的各种释义。此外,使用证明信息的释义检测提高了RTE任务的准确性。

英文摘要:

How to identify, extract, and use phrasal knowledge is a crucial problem for the task of Recognizing Textual Entailment (RTE). To solve this problem, we propose a method for detecting paraphrases via natural deduction proofs of semantic relations between sentence pairs. Our solution relies on a graph reformulation of partial variable unifications and an algorithm that induces subgraph alignments between meaning representations. Experiments show that our method can automatically detect various paraphrases that are absent from existing paraphrase databases. In addition, the detection of paraphrases using proof information improves the accuracy of RTE tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑