文章詳目資料

Journal of Computers EIMEDLINEScopus

  • 加入收藏
  • 下載文章
篇名 A Semantic Enhanced Topic Model Based on Bi-directional LSTM Networks
卷期 30:6
作者 Wang Gao 、 Zhi-feng Yang 、 Hai Wang 、 Fan Zhang 、 Yuan Fang
頁次 060-072
關鍵字 bi-directional LSTM 、 semantic enhancement 、 topic model 、 word embedding 、 EI 、 MEDLINE 、 Scopus
出刊日期 201912
DOI 10.3966/199115992019123006005

中文摘要

英文摘要

Topic modeling techniques are widely used for text modeling and analysis. However, they suffer from the sparseness problem and the complex inference process, which can be alleviated by deep learning techniques such as bi-directional long short-term memory (LSTM) networks. To explore the combination of topic modeling and bi-directional LSTM, we propose a new probabilistic topic model, named GPU-LDA-LSTM. Differently from existing approaches, we first design a document semantic coding framework based on bi-directional LSTM (DSCLSTM) to learn the representation of documents. Then, we utilize the document-topic and wordword dual-generalized Polya urn (GPU) mechanism to enhance semantics. Furthermore, a LSTM network is also used to improve the contextual consistency in the parameter inference process. Experimental results on two real-world datasets show that our model significantly outperforms state-of-the-art models on several evaluation metrics, suggesting that it can extract more meaningful topics.

本卷期文章目次

查看更多

關鍵知識WIKI

查看更多

相關文獻