Peng, Min and Shi, Hongliang and Xie, Qianqian and Zhang, Yihan and Wang, Hua and Li, Zhaoyunfei and Yong, Jianming (2018) Block Bayesian Sparse Topical Coding. In: 2018 IEEE 22nd International Conference on Computer Supported Cooperative Work in Design, 9-11 May 2018, Nanjing, China.
Abstract
Learning low dimensional representations from a large number of short corpora has a profound practical significance but with vital challenge in content analysis and data mining applications. In this paper, we propose a novel topic model called Block Bayesian Sparse Topic Coding (Block-BSTC), which is capable of discovering the latent semantic representation of short texts. The Block-BSTC relaxes the normalization constraint of the inferred representations with word embeddings and block sparse Bayesian learning, which is convenient to directly control the sparsity of word codes with exploiting the intra-block correlations. Furthermore, the experimental results show that Block-BSTC achieves great performance on the sparsity ratio of word codes. Meanwhile, it can improve the accuracy of document classification.
|
Statistics for this ePrint Item |
| Item Type: | Conference or Workshop Item (Commonwealth Reporting Category E) (Paper) |
|---|---|
| Refereed: | Yes |
| Item Status: | Live Archive |
| Additional Information: | Files associated with this item cannot be displayed due to copyright restrictions. |
| Faculty/School / Institute/Centre: | Current - Faculty of Business, Education, Law and Arts - School of Management and Enterprise (1 July 2013 -) |
| Faculty/School / Institute/Centre: | Current - Faculty of Business, Education, Law and Arts - School of Management and Enterprise (1 July 2013 -) |
| Date Deposited: | 07 Feb 2020 06:51 |
| Last Modified: | 06 Mar 2020 04:24 |
| Uncontrolled Keywords: | Sparse Topical Coding, Block Bayesian Sparse Learning, word embeddings |
| Fields of Research : | 08 Information and Computing Sciences > 0806 Information Systems > 080699 Information Systems not elsewhere classified |
| Identification Number or DOI: | 10.1109/CSCWD.2018.8465366 |
| URI: | http://eprints.usq.edu.au/id/eprint/35585 |
Actions (login required)
 |
Archive Repository Staff Only |