The Library
ATM : Adversarial-neural topic model
Tools
Tools
Tools
Wang, Rui, Zhou, Deyu and He, Yulan (2019) ATM : Adversarial-neural topic model. Information Processing & Management, 56 (6). 102098. doi:10.1016/j.ipm.2019.102098
![[img]](http://wrap.warwick.ac.uk/style/images/fileicons/application_pdf.png) |
PDF
WRAP-ATM-adversarial-neural-topic-model-He-2019.pdf - Accepted Version Embargoed item. Restricted access to Repository staff only until 17 August 2020. Contact author directly, specifying your specific needs. - Requires a PDF viewer. Download (889Kb) |
Official URL: http://doi.org/10.1016/j.ipm.2019.102098
Abstract
Topic models are widely used for thematic structure discovery in text. But traditional topic models often require dedicated inference procedures for specific tasks at hand. Also, they are not designed to generate word-level semantic representations. To address the limitations, we propose a neural topic modeling approach based on the Generative Adversarial Nets (GANs), called Adversarial-neural Topic Model (ATM) in this paper. To our best knowledge, this work is the first attempt to use adversarial training for topic modeling. The proposed ATM models topics with Dirichlet prior and employs a generator network to capture the semantic patterns among latent topics. Meanwhile, the generator could also produce word-level semantic representations. Besides, to illustrate the feasibility of porting ATM to tasks other than topic modeling, we apply ATM for open domain event extraction. To validate the effectiveness of the proposed ATM, two topic modeling benchmark corpora and an event dataset are employed in the experiments. Our experimental results on benchmark corpora show that ATM generates more coherence topics (considering five topic coherence measures), outperforming a number of competitive baselines. Moreover, the experiments on event dataset also validate that the proposed approach is able to extract meaningful events from news articles.
| Item Type: | Journal Article | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Subjects: | Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software | ||||||||
| Divisions: | Faculty of Science > Computer Science | ||||||||
| Journal or Publication Title: | Information Processing & Management | ||||||||
| Publisher: | Elsevier | ||||||||
| ISSN: | 0306-4573 | ||||||||
| Official Date: | November 2019 | ||||||||
| Dates: |
|
||||||||
| Date of first compliant deposit: | 14 September 2019 | ||||||||
| Volume: | 56 | ||||||||
| Number: | 6 | ||||||||
| Article Number: | 102098 | ||||||||
| DOI: | 10.1016/j.ipm.2019.102098 | ||||||||
| Status: | Peer Reviewed | ||||||||
| Publication Status: | Published | ||||||||
| Access rights to Published version: | Restricted or Subscription Access | ||||||||
| Copyright Holders: | Elsevier Ltd. | ||||||||
| Open Access Version: |
Request changes or add full text files to a record
Repository staff actions (login required)
 |
View Item |
