计算机科学 ›› 2017, Vol. 44 ›› Issue (5): 241-244.doi: 10.11896/j.issn.1002-137X.2017.05.043
何天雄,李培峰,朱巧明
HE Tian-xiong, LI Pei-feng and ZHU Qiao-ming
摘要: 事件事实性指出了事件发生与否的确定性程度,是自然语言理解的基础。在研究过程中,针对中文事件的事实性识别问题,提出了一种基于特征工程的有效识别方法。该方法选取事件的事实性相关信息进行特征的处理和转化。同时,考虑到部分特征与事件事实性之间的联系,依据规则进行特征融合。实验证明,相比基于规则的事件事实性识别方法,该方法有着更好的识别效果。
[1] CAO Y,ZHU Q M,LI P F.The Construction of Chinese Event Factuality Corpus[J].Journal of Chinese Information Proces-sing,2013,7(6):38-44(in Chinese) 曹媛,朱巧明,李培峰.中文事件事实性信息语料库的构建方法[J].中文信息学报,2013,27(6):38-44. [2] CAO Y,ZHU Q M,LI P F.3D Representation of Chinese Event Factuality[C]∥Chinese Lexical Semantic Workshop.2014:7-13. [3] SAUR R.A factuality profiler for eventualities in text[M].ProQuest,2008. [4] SAUR R,PUSTEJOVSKY J.FactBank:a corpus annotatedwith event factuality[J].Language Resources & Evaluation,2009,43(3):227-268. [5] DIAB M T,LEVIN L,MITAMURA T,et al.Committed belief annotation and tagging[C]∥ Proceedings of the Third Linguistic Annotation Workshop(LAW).2009:68-73. [6] PRABHAKARAN V,RAMBOW O,DIAB M.Automatic committed belief tagging[C]∥International Conference on Computational Linguistics.2010:1014-1022. [7] VELLDAL E,READ J.Factuality detection on the cheap:inferring factuality for increased prec-isionin detecting negated events[C]∥Proceedings of the Workshop on Extra-Propositional Aspects of Meaning in Computational Linguistics.2012:28-36. [8] QIAN Z,LI P F,ZHU Q M.A Two-Step Approach for Event Factuality Identification[C]∥The 19th International Conference on Asian Language Processing.2015:10-16. [9] KILICOGLU H,ROSEMBLAT G,CAIRELLI M J,et al.ACompositional Interpretation of Biomedical Event Factuality[J].ExProM 2015,2015,2(3):16-26. [10] GLAVA G,NAJDER J,BAiC′ B D.Are You for Real?Learning Event Factuality in Cro-atian Texts[C]∥Information Society 2012-Conference on Data Mining and Data Warehouses.2012:18-22. [11] LEE K,ARTZI Y,CHOI Y,et al.Event Detection and Factuality Assessment with Non-Expert Supervision[J].Computer Scien-ce & Engineering,2015,2(2):18-24. |
No related articles found! |
|