An enhanced short text categorization model with deep abundant representation

Yanhui GU, Min GU, Yi LONG, Guandong XU, Zhenglu YANG, Junsheng ZHOU, Weiguang QU

Research output: Contribution to journalArticlespeer-review

13 Citations (Scopus)

Abstract

Short text categorization is a crucial issue to many applications, e.g., Information Retrieval, Question-Answering System, MRI Database Construction and so forth. Many researches focus on data sparsity and ambiguity issues in short text categorization. To tackle these issues, we propose a novel short text categorization strategy based on abundant representation, which utilizes Bi-directional Recurrent Neural Network(Bi-RNN) with Long Short-Term Memory(LSTM) and topic model to catch more contextual and semantic information. Bi-RNN enriches contextual information, and topic model discovers more latent semantic information for abundant text representation of short text. Experimental results demonstrate that the proposed model is comparable to state-of-the-art neural network models and method proposed is effective. Copyright © 2018 Springer Science+Business Media, LLC, part of Springer Nature.

Original languageEnglish
Pages (from-to)1705-1719
JournalWorld Wide Web
Volume21
Early online dateApr 2018
DOIs
Publication statusPublished - Nov 2018

Citation

Gu, Y., Gu, M., Long, Y., Xu, G., Yang, Z., Zhou, J., & Qu, W. (2018). An enhanced short text categorization model with deep abundant representation. World Wide Web, 21, 1705-1719. https://doi.org/10.1007/s11280-018-0542-9

Keywords

  • Short text categorization
  • Topic model
  • Bi-directional LSTM

Fingerprint

Dive into the research topics of 'An enhanced short text categorization model with deep abundant representation'. Together they form a unique fingerprint.