跳到主要导航 跳到搜索 跳到主要内容

Entire information attentive GRU for text representation

  • Wuhan University

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

Recurrent Neural Networks (RNNs), such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), have been widely utilized in sequence representation. However, RNNs neglect variational information and long-term dependency. In this paper, we propose a new neural network structure for extracting a comprehension sequence embedding by handling the entire representation of the sequence. Unlike previous works that put attention mechanism after all steps of GRU, we add the entire representation to the input of the GRU which means the GRU model takes the entire information of the sequence into consideration in every step. We provide three various strategies to adding the entire information which are the Convolutional Neural Network (CNN) based attentive GRU (CBAG), the GRU inner attentive GRU (GIAG) and the pre-trained GRU inner attentive GRU (Pre-GIAG). To evaluate our proposed methods, we conduct extensive experiments on a benchmark sentiment classification dataset. Our experimental results show that our models outperform state-of-the-art baselines significantly.

源语言英语
主期刊名ICTIR 2018 - Proceedings of the 2018 ACM SIGIR International Conference on the Theory of Information Retrieval
出版商Association for Computing Machinery, Inc
页163-166
页数4
ISBN(电子版)9781450356565
DOI
出版状态已出版 - 10 9月 2018
已对外发布是
活动8th ACM SIGIR International Conference on the Theory of Information Retrieval, ICTIR 2018 - Tianjin, 中国
期限: 14 9月 2018 → 17 9月 2018

丛书

姓名ICTIR 2018 - Proceedings of the 2018 ACM SIGIR International Conference on the Theory of Information Retrieval

会议

会议8th ACM SIGIR International Conference on the Theory of Information Retrieval, ICTIR 2018
国家/地区中国
市Tianjin
时期14/09/18 → 17/09/18

学术指纹

探究 'Entire information attentive GRU for text representation' 的科研主题。它们共同构成独一无二的学术指纹。

引用此