Cluster-Gated Convolutional Neural Network for Short Text Classification
Zhang HD(张海东); Ni WC(倪晚成); Zhao MJ(赵美静); Lin ZQ(林子琦)
2019
会议名称23rd Conference on Computational Natural Language Learning(CoNLL)
会议录名称Proceedings of the 23rd Conference on Computational Natural Language Learning
会议日期2019-11-3
会议地点香港
出版地香港
出版者Association for Computational Linguistics
摘要

Text classification plays a crucial role for understanding natural language in a wide range of applications. Most existing approaches mainly focus on long text classification (e.g., blogs, documents, paragraphs). However, they cannot easily be applied to short text because of its sparsity and lack of context. In this paper, we propose a new model called cluster-gated convolutional neural network (CGCNN), which jointly explores word-level clustering and text classification in an end-to-end manner. Specifically, the proposed model firstly uses a bi-directional long short-term memory to learn word representations. Then, it leverages a soft clustering method to explore their semantic relation with the cluster centers, and takes linear transformation on text representations. It develops a cluster-dependent gated convolutional layer to further control the cluster-dependent feature flows. Experimental results on five commonly used datasets show that our model outperforms state-of-the-art models.

收录类别SCI
七大方向——子方向分类自然语言处理
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/41467
专题复杂系统认知与决策实验室_智能系统与工程
通讯作者Ni WC(倪晚成)
作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Zhang HD,Ni WC,Zhao MJ,et al. Cluster-Gated Convolutional Neural Network for Short Text Classification[C]. 香港:Association for Computational Linguistics,2019.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
2019-CoNLL.pdf(1310KB)会议论文 开放获取CC BY-NC-SA浏览
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
[Zhang HD(张海东)]的文章
[Ni WC(倪晚成)]的文章
[Zhao MJ(赵美静)]的文章
百度学术
百度学术中相似的文章
[Zhang HD(张海东)]的文章
[Ni WC(倪晚成)]的文章
[Zhao MJ(赵美静)]的文章
必应学术
必应学术中相似的文章
[Zhang HD(张海东)]的文章
[Ni WC(倪晚成)]的文章
[Zhao MJ(赵美静)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 2019-CoNLL.pdf
格式: Adobe PDF
此文件暂不支持浏览
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。