Singleton detection for coreference resolution via multi-window and multi-filter CNN

Kenan Li, Heyan Huang*, Yuhang Guo, Ping Jian

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

2 引用 (Scopus)

摘要

Mention detection is the first and a key stage in most of coreference resolution systems. Singleton mentions are the ones which appear only once and are not mentioned in the following texts. Singleton mentions always affect the performance of coreference resolution systems. To remove the singleton ones from the automatically predicted mentions, we propose a novel singleton detection method based on multi-window and multi-filter convolutional neural network (MMCNN). The MMCNN model can detect singleton mentions with less use of hand-designed features and more sentence information. Experiments show that our system outperforms all the existing singleton detection systems.

源语言英语
主期刊名Machine Translation - 13th China Workshop, CWMT 2017, Revised Selected Papers
编辑Derek F. Wong, Deyi Xiong
出版商Springer Verlag
9-19
页数11
ISBN(印刷版)9789811071331
DOI
出版状态已出版 - 2017
活动13th China Workshop on Machine Translation, CWMT 2017 - Dalian, 中国
期限: 27 9月 201729 9月 2017

出版系列

姓名Communications in Computer and Information Science
787
ISSN(印刷版)1865-0929

会议

会议13th China Workshop on Machine Translation, CWMT 2017
国家/地区中国
Dalian
时期27/09/1729/09/17

指纹

探究 'Singleton detection for coreference resolution via multi-window and multi-filter CNN' 的科研主题。它们共同构成独一无二的指纹。

引用此