基于局部语义相关性的定义文本义原预测

作为人类语言的最小语义单位,义原已被成功应用于许多自然语言处理任务。人工构造和更新义原知识库成本较大,因此义原预测被用来辅助义原标注。该文探索了利用定义文本为词语自动预测义原的方法。词语的各个义原通常都与定义文本中的不同词语的语义有相关关系,这种现象被称为局部语义相关性。与之对应,该文提出了义原相关池化(SCorP)模型,该模型能够利用局部语义相关性来预测义原。在HowNet上的评测结果表明,SCorP取得了当前最好的义原预测性能。大量的定量分析进一步证明了SCorP模型能够正确地学习义原与定义文本之间的局部语义相关性。

Lexical Sememe Prediction by Dictionary Definitions and LocalSemantic Correspondence

Sememes, defined as the minimum semantic units of human languages in linguistics, have been proven useful in many NLP tasks. Since manual construction and update of sememe knowledge bases (KBs) are costly, the task of automatic sememe prediction has been used to assist sememe annotation. In this paper, we explore the method of applying dictionary definitions to predicting sememes for unannotated words. We find that sememes of each word are usually semantically related to different words in its dictionary definition, and we name this matching relationship local semantic correspondence. Accordingly, we propose a Sememe Correspondence Pooling (SCorP) model which is able to capture this kind of matching to predict sememes. Evaluated on HowNet, our model is revealed with state-of-the-art performance, capable of properly learning local semantic correspondence between sememes and words in dictionary definitions.