文献类型：期刊文献

英文题名：Inference of isA commonsense knowledge with lexical taxonomy

作者：Wang, Chao[1];Liu, Jingping[2];Liu, Juntao[1];Wang, Wei[1]

机构：[1]Fudan Univ, Shanghai Key Lab Data Sci, Sch Comp Sci, Shanghai, Peoples R China;[2]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai, Peoples R China

年份：2023

卷号：53

期号：5

起止页码：5290

外文期刊名：APPLIED INTELLIGENCE

收录：;EI(收录号：20222612263352);WOS:【SCI-EXPANDED(收录号:WOS:000814444400003)】；

基金：This work was supported by the National Key R&D Program of China under Grant 2018YFB1403200.

语种：英文

外文关键词：isA commonsense knowledge; Knowledge graph; Lexical taxonomy

摘要：Commonsense knowledge is a crucial resource to help the machine understand the human world. However, the conventional methods of extracting commonsense knowledge with isA relation (or isA commonsense knowledge) from text corpora generally do not work well since commonsense knowledge is typically omitted in communication. In this paper, we mainly focus on the inference of isA commonsense knowledge (the definition of isA here to express a hypernym-hyponym relationship and we concentrate on whether the description of (s, isA, o) is correct based on this relationship, e.g., (mammal, isA, animal), (Hello Kitty, isA, cat)) with a special kind of knowledge graph: lexical taxonomy. Lexical and semantic features of terms are both extracted from three relationships including exclusive, compatible, andinclusive relationships then a simple but effective classification model is further utilized to predict whether isA commonsense holds or not. Besides, we implement our model on a lexical taxonomy: Probase. A series of comparative experiments prove the effectiveness of our approach with an accuracy of over 96%, and we infer 200k isA commonsense knowledge from 1 million new pairs.