Logical Inference on Dependency-based Compositional Semantics

Logical Inference on Dependency-based Compositional Semantics
复制标题

DOI:
10.3115/v1/p14-1008
复制
发表时间:
2014-06
期刊:
--
影响因子:
--
通讯作者:
Ran Tian;Yusuke Miyao;Takuya Matsuzaki
Ran Tian;Yusuke Miyao;Takuya Matsuzaki
中科院分区:
其他
文献类型:
--
作者:
Ran Tian;Yusuke Miyao;Takuya Matsuzaki

文献摘要

被引文献

相似文献

基于依赖的组合语义学(DCS)是一个自然语言语义框架,具有易于处理的结构和严格的语义。在本文中,我们配备了DCS框架与逻辑推理,通过定义抽象表示作为一个抽象的表示在原始DCS的计算过程。建立了一个推理机来实现对抽象表示的推理。此外,我们提出了一种方法来生成在逻辑推理的飞行知识,通过结合我们的框架与树变换的想法。在FraCaS和PASCAL RTE数据集上的实验显示了良好的效果。
Dependency-based Compositional Semantics (DCS) is a framework of natural language semantics with easy-to-process structures as well as strict semantics. In this paper, we equip the DCS framework with logical inference, by defining abstract denotations as an abstraction of the computing process of denotations in original DCS. An inference engine is built to achieve inference on abstract denotations. Furthermore, we propose a way to generate on-the-fly knowledge in logical inference, by combining our framework with the idea of tree transformation. Experiments on FraCaS and PASCAL RTE datasets show promising results.