Cold-start aware deep memory networks for multi-entity aspect-based sentiment analysis

Various types of target information have been considered in aspect-based sentiment analysis, such as entities and aspects. Existing research has realized the importance of targets and developed methods with the goal of precisely modeling their contexts via generating target-specific representations....

Full description

Saved in:
Bibliographic Details
Main Authors: SONG, Kaisong, GAO, Wei, ZHAO, Lujun, SUN, Changlong, LIU, Xiaozhong
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2019
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/4558
https://ink.library.smu.edu.sg/context/sis_research/article/5561/viewcontent/0722.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-5561
record_format dspace
spelling sg-smu-ink.sis_research-55612019-12-26T08:33:12Z Cold-start aware deep memory networks for multi-entity aspect-based sentiment analysis SONG, Kaisong GAO, Wei ZHAO, Lujun SUN, Changlong LIU, Xiaozhong Various types of target information have been considered in aspect-based sentiment analysis, such as entities and aspects. Existing research has realized the importance of targets and developed methods with the goal of precisely modeling their contexts via generating target-specific representations. However, all these methods ignore that these representations cannot be learned well due to the lack of sufficient human-annotated target-related reviews, which leads to the data sparsity challenge, a.k.a. cold-start problem here. In this paper, we focus on a more general multiple entity aspect-based sentiment analysis (ME-ABSA) task which aims at identifying the sentiment polarity of different aspects of multiple entities in their context. Faced with severe cold-start scenario, we develop a novel and extensible deep memory network framework with cold-start aware computational layers which use frequency-guided attention mechanism to accentuate on the most related targets, and then compose their representations into a complementary vector for enhancing the representations of cold-start entities and aspects. To verify the effectiveness of the framework, we instantiate it with a concrete context encoding method and then apply the model to the ME-ABSA task. Experimental results conducted on two public datasets demonstrate that the proposed approach outperforms state-of-the-art baselines on ME-ABSA task. 2019-08-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/4558 info:doi/10.24963/ijcai.2019/722 https://ink.library.smu.edu.sg/context/sis_research/article/5561/viewcontent/0722.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Natural Language Processing Sentiment Analysis and Text Mining Natural Language Processing Text Classification Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Natural Language Processing
Sentiment Analysis and Text Mining
Natural Language Processing
Text Classification
Databases and Information Systems
spellingShingle Natural Language Processing
Sentiment Analysis and Text Mining
Natural Language Processing
Text Classification
Databases and Information Systems
SONG, Kaisong
GAO, Wei
ZHAO, Lujun
SUN, Changlong
LIU, Xiaozhong
Cold-start aware deep memory networks for multi-entity aspect-based sentiment analysis
description Various types of target information have been considered in aspect-based sentiment analysis, such as entities and aspects. Existing research has realized the importance of targets and developed methods with the goal of precisely modeling their contexts via generating target-specific representations. However, all these methods ignore that these representations cannot be learned well due to the lack of sufficient human-annotated target-related reviews, which leads to the data sparsity challenge, a.k.a. cold-start problem here. In this paper, we focus on a more general multiple entity aspect-based sentiment analysis (ME-ABSA) task which aims at identifying the sentiment polarity of different aspects of multiple entities in their context. Faced with severe cold-start scenario, we develop a novel and extensible deep memory network framework with cold-start aware computational layers which use frequency-guided attention mechanism to accentuate on the most related targets, and then compose their representations into a complementary vector for enhancing the representations of cold-start entities and aspects. To verify the effectiveness of the framework, we instantiate it with a concrete context encoding method and then apply the model to the ME-ABSA task. Experimental results conducted on two public datasets demonstrate that the proposed approach outperforms state-of-the-art baselines on ME-ABSA task.
format text
author SONG, Kaisong
GAO, Wei
ZHAO, Lujun
SUN, Changlong
LIU, Xiaozhong
author_facet SONG, Kaisong
GAO, Wei
ZHAO, Lujun
SUN, Changlong
LIU, Xiaozhong
author_sort SONG, Kaisong
title Cold-start aware deep memory networks for multi-entity aspect-based sentiment analysis
title_short Cold-start aware deep memory networks for multi-entity aspect-based sentiment analysis
title_full Cold-start aware deep memory networks for multi-entity aspect-based sentiment analysis
title_fullStr Cold-start aware deep memory networks for multi-entity aspect-based sentiment analysis
title_full_unstemmed Cold-start aware deep memory networks for multi-entity aspect-based sentiment analysis
title_sort cold-start aware deep memory networks for multi-entity aspect-based sentiment analysis
publisher Institutional Knowledge at Singapore Management University
publishDate 2019
url https://ink.library.smu.edu.sg/sis_research/4558
https://ink.library.smu.edu.sg/context/sis_research/article/5561/viewcontent/0722.pdf
_version_ 1770574913823834112