Investigating Siamese LSTM networks for text categorization

Chin Hong Shih, Bi Cheng Yan, Shih Hung Liu, Berlin Chen

研究成果: 書貢獻/報告類型會議貢獻

5 引文 斯高帕斯(Scopus)

摘要

Recently, deep learning and deep neural networks have attracted considerable attention and emerged as one predominant field of research in the artificial intelligence community. The developed techniques have also gained widespread use in various domains with good success, such as automatic speech recognition, information retrieval and text classification, etc. Among them, long short-term memory (LSTM) networks are well suited to such tasks, which can capture long-range dependencies among words efficiently, meanwhile alleviating the gradient vanishing or exploding problem during training effectively. Following this line of research, in this paper we explore a novel use of a Siamese LSTM based method to learn more accurate document representation for text categorization. Such a network architecture takes a pair of documents with variable lengths as the input and utilizes pairwise learning to generate distributed representations of documents that can more precisely render the semantic distance between any pair of documents. In doing so, documents associated with the same semantic or topic label could be mapped to similar representations having a relatively higher semantic similarity. Experiments conducted on two benchmark text categorization tasks, viz. IMDB and 20Newsgroups, show that using a three-layer deep neural network based classifier that takes a document representation learned from the Siamese LSTM sub-networks as the input can achieve competitive performance in relation to several state-of-the-art methods.

原文英語
主出版物標題Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
發行者Institute of Electrical and Electronics Engineers Inc.
頁面641-646
頁數6
ISBN(電子)9781538615423
DOIs
出版狀態已發佈 - 2018 二月 5
事件9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 - Kuala Lumpur, 马来西亚
持續時間: 2017 十二月 122017 十二月 15

出版系列

名字Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
2018-February

會議

會議9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
國家马来西亚
城市Kuala Lumpur
期間17/12/1217/12/15

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Information Systems
  • Signal Processing

指紋 深入研究「Investigating Siamese LSTM networks for text categorization」主題。共同形成了獨特的指紋。

  • 引用此

    Shih, C. H., Yan, B. C., Liu, S. H., & Chen, B. (2018). Investigating Siamese LSTM networks for text categorization. 於 Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 (頁 641-646). (Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017; 卷 2018-February). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APSIPA.2017.8282104