On-demand Injection of Lexical Knowledge for Recognising Textual Entailment
On-demand Injection of Lexical Knowledge for Recognising Textual Entailment
复制标题
DOI：
10.18653/v1/e17-1067
复制
发表时间：
2017-04
期刊：
影响因子：
--
通讯作者：
Pascual Martínez-Gómez;K. Mineshima;Yusuke Miyao;D. Bekki
中科院分区：
文献类型：
--
作者：
Pascual Martínez-Gómez;K. Mineshima;Yusuke Miyao;D. Bekki
我们使用逻辑语义表示和定理证明来实现文本蕴涵的识别。在这种情况下，需要明确地说明源文本和目标文本之间保留语义蕴涵的词汇差异。然而，识别次句语义关系并非易事。我们通过监控定理的证明和检测与逻辑前提共享谓词参数的不可证明子目标来解决这个问题。如果存在语言关系，则按需构造一个适当的公理，并继续定理证明。实验表明，这种方法是有效和精确的，产生的系统优于其他基于逻辑的系统，并与最先进的统计方法竞争。
We approach the recognition of textual entailment using logical semantic representations and a theorem prover. In this setup, lexical divergences that preserve semantic entailment between the source and target texts need to be explicitly stated. However, recognising subsentential semantic relations is not trivial. We address this problem by monitoring the proof of the theorem and detecting unprovable sub-goals that share predicate arguments with logical premises. If a linguistic relation exists, then an appropriate axiom is constructed on-demand and the theorem proving continues. Experiments show that this approach is effective and precise, producing a system that outperforms other logic-based systems and is competitive with state-of-the-art statistical methods.