面向事件的多通道筛选模块

2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE) Pub Date : 2015-11-01 DOI:10.1109/ISKE.2015.56

Qiang Li, Zongtian Liu, Lei Chen, Xianchuan Wang

{"title":"面向事件的多通道筛选模块","authors":"Qiang Li, Zongtian Liu, Lei Chen, Xianchuan Wang","doi":"10.1109/ISKE.2015.56","DOIUrl":null,"url":null,"abstract":"Coreference resolution is one of the key issues in the natural language processing, it can eliminate uncertain problems of event in the event-oriented natural language processing, and that is important for the upper application of event. This paper builds an event-oriented multi-pass sieve module for coreference resolution, and combined with the characteristics of the event, we add the constraint conditions to each sieve to improve the accuracy of each sieve. We use this module to carry on experiment for object elements of the event. Compared with machine learning method based on C4.5 decision tree, it has a very big enhancement on the performance.","PeriodicalId":312629,"journal":{"name":"2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"An Event-Oriented Multi-pass Sieve Module for Coreference Resolution\",\"authors\":\"Qiang Li, Zongtian Liu, Lei Chen, Xianchuan Wang\",\"doi\":\"10.1109/ISKE.2015.56\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Coreference resolution is one of the key issues in the natural language processing, it can eliminate uncertain problems of event in the event-oriented natural language processing, and that is important for the upper application of event. This paper builds an event-oriented multi-pass sieve module for coreference resolution, and combined with the characteristics of the event, we add the constraint conditions to each sieve to improve the accuracy of each sieve. We use this module to carry on experiment for object elements of the event. Compared with machine learning method based on C4.5 decision tree, it has a very big enhancement on the performance.\",\"PeriodicalId\":312629,\"journal\":{\"name\":\"2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISKE.2015.56\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISKE.2015.56","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

共同参照解析是自然语言处理中的关键问题之一，它可以消除面向事件的自然语言处理中事件的不确定性问题，对事件的上层应用具有重要意义。本文构建了面向事件的多通道共参解析筛选模块，并结合事件的特点，在每个筛选中加入约束条件，提高每个筛选的精度。我们利用该模块对事件的对象元素进行实验。与基于C4.5决策树的机器学习方法相比，在性能上有很大的提升。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

An Event-Oriented Multi-pass Sieve Module for Coreference Resolution

Coreference resolution is one of the key issues in the natural language processing, it can eliminate uncertain problems of event in the event-oriented natural language processing, and that is important for the upper application of event. This paper builds an event-oriented multi-pass sieve module for coreference resolution, and combined with the characteristics of the event, we add the constraint conditions to each sieve to improve the accuracy of each sieve. We use this module to carry on experiment for object elements of the event. Compared with machine learning method based on C4.5 decision tree, it has a very big enhancement on the performance.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)

自引率

0.00%

发文量