The Library
Aspect-invariant sentiment feature learning : adversarial multi-task learning for aspect-based sentiment analysis
Tools
Liang, Bin, Yin, Rongdi, Gui, Lin, Du, Jiachen, He, Yulan and Xu, Ruifeng (2020) Aspect-invariant sentiment feature learning : adversarial multi-task learning for aspect-based sentiment analysis. In: 28th ACM International Conference on Information and Knowledge Management (CIKM), Virtual conference, 18-23 Oct 2020. Published in: CIKM '20: Proceedings of the 29th ACM International Conference on Information & Knowledge Management pp. 825-834. ISBN 9781450368599. doi:10.1145/3340531.3411868
|
PDF
WRAP-aspect-invariant-sentiment-feature-learning-adversarial-multi-task-learning-aspect-based-sentiment-analysis-Gui-2020.pdf - Accepted Version - Requires a PDF viewer. Download (6Mb) | Preview |
Official URL: https://doi.org/10.1145/3340531.3411868
Abstract
In most previous studies, the aspect-related text is considered an important clue for the Aspect-based Sentiment Analysis (ABSA) task, and thus various attention mechanisms have been proposed to leverage the interactions between aspects and context. However, it is observed that some sentiment expressions carry the same polarity regardless of the aspects they are associated with. In such cases, it is not necessary to incorporate aspect information for ABSA. More observations on the experimental results show that blindly leveraging interactions between aspects and context as features may introduce noises when analyzing those aspect-invariant sentiment expressions, especially when the aspect-related annotated data is insufficient. Hence, in this paper, we propose an Adversarial Multi-task Learning framework to identify the aspect-invariant/dependent sentiment expressions without extra annotations. In addition, we adopt a gating mechanism to control the contribution of representations derived from aspect-invariant and aspect-dependent hidden states when generating the final contextual sentiment representations for the given aspect. This essentially allows the exploitation of aspect-invariant sentiment features for better ABSA results. Experimental results on two benchmark datasets show that extending existing neural models using our proposed framework achieves superior performance. In addition, the aspect-invariant data extracted by the proposed framework can be considered as pivot features for better transfer learning of the ABSA models on unseen aspects.
Item Type: | Conference Item (Paper) | ||||||
---|---|---|---|---|---|---|---|
Subjects: | Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software | ||||||
Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science | ||||||
Library of Congress Subject Headings (LCSH): | Natural language processing (Computer science), Data mining, Sentiment analysis , Computer multitasking | ||||||
Journal or Publication Title: | CIKM '20: Proceedings of the 29th ACM International Conference on Information & Knowledge Management | ||||||
Publisher: | ACM | ||||||
ISBN: | 9781450368599 | ||||||
Official Date: | 19 October 2020 | ||||||
Dates: |
|
||||||
Page Range: | pp. 825-834 | ||||||
DOI: | 10.1145/3340531.3411868 | ||||||
Status: | Peer Reviewed | ||||||
Publication Status: | Published | ||||||
Reuse Statement (publisher, data, author rights): | "© ACM, 2020. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in 28th ACM International Conference on Information and Knowledge Management (CIKM) Oct 2020 http://doi.acm.org/10.1145/3340531.3411868 | ||||||
Access rights to Published version: | Restricted or Subscription Access | ||||||
Date of first compliant deposit: | 23 July 2020 | ||||||
Date of first compliant Open Access: | 3 August 2021 | ||||||
Conference Paper Type: | Paper | ||||||
Title of Event: | 28th ACM International Conference on Information and Knowledge Management (CIKM) | ||||||
Type of Event: | Conference | ||||||
Location of Event: | Virtual conference | ||||||
Date(s) of Event: | 18-23 Oct 2020 | ||||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year