文章基本信息

标题：EMPLOYING SEMANTIC KNOWLEDGE ON EVENT TRIGGER CLUSTERING
本地全文：下载
作者：ADE ROMADHONY ; DWI H WIDYANTORO ; AYU PURWARIANTI 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2017
卷号：95
期号：6
出版社：Journal of Theoretical and Applied
摘要：Formerly, most of information extraction systems require the predefined template in order to extract the structured information. Extracting information without predefined template leads to the needs of extracting the template. We propose an approach on event template extraction by clustering the event trigger using semantic similarity information from WordNet synset gloss. We demonstrate in the experiment that the semantic information from WordNet synset gloss improves the event trigger clusters quality. The evaluation result shows that the clusters from WordNet synset gloss achieve the top performance on 8 out of 16 event types, outperform the other approaches. The other approaches that we compared on evaluation including: using co-occurrence information only, using relation similarity from UMBC system, and the combination of co-occurrence and relation similarity.
关键词：WordNet; Semantic Knowledge; Synset Gloss; Event Trigger; Clustering