Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling

	Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling
	Peng Zhou; Zhenyu Qi; Suncong Zheng; Jiaming Xu; Hongyun Bao; Bo Xu
	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/173211/41125
专题	复杂系统认知与决策实验室_听觉模型与认知计算
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.