Convolutional Neural Network with Word Embeddings for Chinese Word Segmentation
Wang CQ(汪春奇)1,2; Xu B(徐波)1
2017
会议名称第八届国际自然语言处理研讨会
页码163-172
会议日期2017年11月
会议地点台北
摘要

Character-based sequence labeling frame- work is flexible and efficient for Chi- nese word segmentation (CWS). Recently, many character-based neural models have been applied to CWS. While they obtain good performance, they have two obvious weaknesses. The first is that they heav- ily rely on manually designed bigram fea- ture, i.e. they are not good at captur- ing n-gram features automatically. The second is that they make no use of full word information. For the first weakness, we propose a convolutional neural model, which is able to capture rich n-gram fea- tures without any feature engineering. For the second one, we propose an effective approach to integrate the proposed model with word embeddings. We evaluate the model on two benchmark datasets: PKU and MSR. Without any feature engineer- ing, the model obtains competitive per- formance — 95.7% on PKU and 97.3% on MSR. Armed with word embeddings, the model achieves state-of-the-art perfor- mance on both datasets — 96.5% on PKU and 98.0% on MSR, without using any ex- ternal labeled resource.

关键词Chinese Word Segmentation Convolutional Neural Network Word Embedding
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/19674
专题数字内容技术与服务研究中心_听觉模型与认知计算
作者单位1.中科院自动化研究所
2.中国科学院大学
推荐引用方式
GB/T 7714
Wang CQ,Xu B. Convolutional Neural Network with Word Embeddings for Chinese Word Segmentation[C],2017:163-172.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
ijcnlp2017.pdf(385KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang CQ(汪春奇)]的文章
[Xu B(徐波)]的文章
百度学术
百度学术中相似的文章
[Wang CQ(汪春奇)]的文章
[Xu B(徐波)]的文章
必应学术
必应学术中相似的文章
[Wang CQ(汪春奇)]的文章
[Xu B(徐波)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: ijcnlp2017.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。