Determining Semantic Textual Similarity using Natural Deduction Proofs
Determining Semantic Textual Similarity using Natural Deduction Proofs
复制标题
DOI：
10.18653/v1/d17-1071
复制
发表时间：
2017-07
期刊：
影响因子：
--
通讯作者：
Hitomi Yanaka;K. Mineshima;Pascual Martínez-Gómez;D. Bekki
中科院分区：
文献类型：
--
作者：
Hitomi Yanaka;K. Mineshima;Pascual Martínez-Gómez;D. Bekki
文本语义相似度的确定是自然语言处理领域的一个核心研究课题。由于用于句子表示的基于向量的模型通常使用浅层信息，因此难以捕获准确的语义。相比之下，逻辑语义表示捕捉更深层次的句子语义，但它们的符号性质不提供文本相似性的分级概念。我们提出了一种方法来确定语义文本相似度相结合的浅层特征提取的自然演绎证明的句子对之间的双向蕴涵关系的特征。对于自然演绎证明，我们使用ccg2lambda，一个高阶自动推理系统，它将组合范畴语法（CCG）派生树转换为语义表示，并进行自然演绎证明。实验表明，我们的系统是能够优于其他基于逻辑的系统，从证明的特征是有效的学习文本相似性。
Determining semantic textual similarity is a core research subject in natural language processing. Since vector-based models for sentence representation often use shallow information, capturing accurate semantics is difficult. By contrast, logical semantic representations capture deeper levels of sentence semantics, but their symbolic nature does not offer graded notions of textual similarity. We propose a method for determining semantic textual similarity by combining shallow features with features extracted from natural deduction proofs of bidirectional entailment relations between sentence pairs. For the natural deduction proofs, we use ccg2lambda, a higher-order automatic inference system, which converts Combinatory Categorial Grammar (CCG) derivation trees into semantic representations and conducts natural deduction proofs. Experiments show that our system was able to outperform other logic-based systems and that features derived from the proofs are effective for learning textual similarity.