CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
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
Conference NameIn Proceedings of the 26th International Conference on Computational Linguistics (COLING2016)
Conference Date2016/12/11-2016/12/16
Conference PlaceOsaka, Japan
AbstractRecurrent 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.
Document Type会议论文
Affiliation1.Institute of Automation, Chinese Academy of Sciences, China
2.Center for Excellence in Brain Science and Intelligence Technology, China
Recommended Citation
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.
Files in This Item: Download All
File Name/Size DocType Version Access License
2016-COLING-Text Cla(285KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Peng Zhou]'s Articles
[Zhenyu Qi]'s Articles
[Suncong Zheng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Peng Zhou]'s Articles
[Zhenyu Qi]'s Articles
[Suncong Zheng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Peng Zhou]'s Articles
[Zhenyu Qi]'s Articles
[Suncong Zheng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2016-COLING-Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.