Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling
Peng Zhou1; Zhenyu Qi1; Suncong Zheng1; Jiaming Xu1; Hongyun Bao1; Bo Xu1,2
2016
会议名称In Proceedings of the 26th International Conference on Computational Linguistics (COLING2016)
页码3485-3495
会议日期2016/12/11-2016/12/16
会议地点Osaka, Japan
摘要Recurrent Neural Network (RNN) is one of the most popular architectures used in Natural Language Processsing (NLP) tasks because its recurrent structure is very suitable to process variablelength text. RNN can utilize distributed representations of words by first converting the tokens comprising each text into vectors, which form a matrix. And this matrix includes two dimensions: the time-step dimension and the feature vector dimension. Then most existing models usually utilize one-dimensional (1D) max pooling operation or attention-based operation only on the time-step dimension to obtain a fixed-length vector. However, the features on the feature vector dimension are not mutually independent, and simply applying 1D pooling operation over the time-step dimension independently may destroy the structure of the feature representation. On the other hand, applying two-dimensional (2D) pooling operation over the two dimensions may sample more meaningful features for sequence modeling tasks. To integrate the features on both dimensions of the matrix, this paper explores applying 2D max pooling operation to obtain a fixed-length representation of the text. This paper also utilizes 2D convolution to sample more meaningful information of the matrix. Experiments are conducted on six text classification tasks, including sentiment analysis, question classification, subjectivity classification and newsgroup classification. Compared with the state-of-the-art models, the proposed models achieve excellent performance on 4 out of 6 tasks. Specifically, one of the proposed models achieves highest accuracy on Stanford Sentiment Treebank binary classification and fine-grained classification tasks.
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/19667
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.Institute of Automation, Chinese Academy of Sciences, China
2.Center for Excellence in Brain Science and Intelligence Technology, China
推荐引用方式
GB/T 7714
Peng Zhou,Zhenyu Qi,Suncong Zheng,et al. Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling[C],2016:3485-3495.
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
2016-COLING-Text Cla(285KB)会议论文 开放获取CC BY-NC-SA浏览 请求全文
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
[Peng Zhou]的文章
[Zhenyu Qi]的文章
[Suncong Zheng]的文章
百度学术
百度学术中相似的文章
[Peng Zhou]的文章
[Zhenyu Qi]的文章
[Suncong Zheng]的文章
必应学术
必应学术中相似的文章
[Peng Zhou]的文章
[Zhenyu Qi]的文章
[Suncong Zheng]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 2016-COLING-Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling.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。