计算机应用研究2016，Vol.33Issue(10)：2895-2897,2901,4.DOI:10.3969/j.issn.1001-3695.2016.10.003
名词短语事件指代消解研究
Research on noun phrase event anaphora resolution
摘要
Abstract
This paper focused on noun phrases event resolution.It improved the semantic features by adding the elements of time and address when computing semantic similarity of tuples (semantic roles information).Experiments on the English por-tion of OntoNotes 4.0 show that the semantic roles information (Argm-Log,Argm-Tmp)can significantly boost the performance of the baseline for event noun phrases resolution.It outperforms the baseline system by 0.49% in precision and 0.2% in F-measure.Consequently,it proves Argm-Log and Argm-Tmp can improve the event noun phrases resolution.关键词
事件指代消解/语义特征/特征提取/机器学习/语料Key words
event anaphora resolution/semantic feature/feature extraction/SVM/OntonOtes 4.0分类
信息技术与安全科学引用本文复制引用
陈耀文,张兴忠,郝晓燕..名词短语事件指代消解研究[J].计算机应用研究,2016,33(10):2895-2897,2901,4.基金项目
山西省自然科学基金资助项目 （）
