Adaptive Region Embedding for Text Classification

Authors

  • Liuyu Xiang Tsinghua University
  • Xiaoming Jin Tsinghua University
  • Lan Yi Cisco
  • Guiguang Ding Tsinghua University

DOI:

https://doi.org/10.1609/aaai.v33i01.33017314

Abstract

Deep learning models such as convolutional neural networks and recurrent networks are widely applied in text classification. In spite of their great success, most deep learning models neglect the importance of modeling context information, which is crucial to understanding texts. In this work, we propose the Adaptive Region Embedding to learn context representation to improve text classification. Specifically, a metanetwork is learned to generate a context matrix for each region, and each word interacts with its corresponding context matrix to produce the regional representation for further classification. Compared to previous models that are designed to capture context information, our model contains less parameters and is more flexible. We extensively evaluate our method on 8 benchmark datasets for text classification. The experimental results prove that our method achieves state-of-the-art performances and effectively avoids word ambiguity.

Downloads

Published

2019-07-17

How to Cite

Xiang, L., Jin, X., Yi, L., & Ding, G. (2019). Adaptive Region Embedding for Text Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 7314-7321. https://doi.org/10.1609/aaai.v33i01.33017314

Issue

Section

AAAI Technical Track: Natural Language Processing