Improving Word Vector with Prior Knowledge in Semantic Dictionary | |
Wei Li ; Yunfang Wu ; Xueqiang Lv | |
2016 | |
关键词 | rare words semantic dictionary morphological information word embedding |
英文摘要 | Using low dimensional vector space to represent words has been very effective in many NLP tasks.However,it doesn't work well when faced with the problem of rare and unseen words.In this paper,we propose to leverage the knowledge in semantic dictionary in combination with some morphological information to build an enhanced vector space.We get an improvement of 2.3%over the state-of-the-art Heidel Time system in temporal expression recognition,and obtain a large gain in other name entity recognition(NER)tasks.The semantic dictionary Hownet alone also shows promising results in computing lexical similarity.; 1-9 |
语种 | 英语 |
出处 | 第五届自然语言处理与中文计算会议(NLPCC-ICCPOL2016)论文集中国计算机学会 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/480637] |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Wei Li,Yunfang Wu,Xueqiang Lv. Improving Word Vector with Prior Knowledge in Semantic Dictionary. 2016-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论