Towards generative aspect-based sentiment analysis

Aspect-based sentiment analysis (ABSA) has received increasing attention recently. Most existing work tackles ABSA in a discriminative manner, designing various task-specific classification networks for the prediction. Despite their effectiveness, these methods ignore the rich label semantics in ABS...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHANG, Wenxuan, LI, Xin, DENG, Yang, BING, Lidong, LAM, Wai
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2021
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/9112
https://ink.library.smu.edu.sg/context/sis_research/article/10115/viewcontent/2021.acl_short.64.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-10115
record_format dspace
spelling sg-smu-ink.sis_research-101152024-08-01T14:47:05Z Towards generative aspect-based sentiment analysis ZHANG, Wenxuan LI, Xin DENG, Yang BING, Lidong LAM, Wai Aspect-based sentiment analysis (ABSA) has received increasing attention recently. Most existing work tackles ABSA in a discriminative manner, designing various task-specific classification networks for the prediction. Despite their effectiveness, these methods ignore the rich label semantics in ABSA problems and require extensive task-specific designs. In this paper, we propose to tackle various ABSA tasks in a unified generative framework. Two types of paradigms, namely annotation-style and extraction-style modeling, are designed to enable the training process by formulating each ABSA task as a text generation problem. We conduct experiments on four ABSA tasks across multiple benchmark datasets where our proposed generative approach achieves new state-of-the-art results in almost all cases. This also validates the strong generality of the proposed framework which can be easily adapted to arbitrary ABSA task without additional taskspecific model design.1. 2021-08-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9112 info:doi/10.18653/v1/2021.acl-short.64 https://ink.library.smu.edu.sg/context/sis_research/article/10115/viewcontent/2021.acl_short.64.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 Analysis problems Benchmark datasets Classification networks Label semantics Sentiment analysis State of the art Task-specific models Text generations Training process Databases and Information Systems Graphics and Human Computer Interfaces Information Security
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Analysis problems
Benchmark datasets
Classification networks
Label semantics
Sentiment analysis
State of the art
Task-specific models
Text generations
Training process
Databases and Information Systems
Graphics and Human Computer Interfaces
Information Security
spellingShingle Analysis problems
Benchmark datasets
Classification networks
Label semantics
Sentiment analysis
State of the art
Task-specific models
Text generations
Training process
Databases and Information Systems
Graphics and Human Computer Interfaces
Information Security
ZHANG, Wenxuan
LI, Xin
DENG, Yang
BING, Lidong
LAM, Wai
Towards generative aspect-based sentiment analysis
description Aspect-based sentiment analysis (ABSA) has received increasing attention recently. Most existing work tackles ABSA in a discriminative manner, designing various task-specific classification networks for the prediction. Despite their effectiveness, these methods ignore the rich label semantics in ABSA problems and require extensive task-specific designs. In this paper, we propose to tackle various ABSA tasks in a unified generative framework. Two types of paradigms, namely annotation-style and extraction-style modeling, are designed to enable the training process by formulating each ABSA task as a text generation problem. We conduct experiments on four ABSA tasks across multiple benchmark datasets where our proposed generative approach achieves new state-of-the-art results in almost all cases. This also validates the strong generality of the proposed framework which can be easily adapted to arbitrary ABSA task without additional taskspecific model design.1.
format text
author ZHANG, Wenxuan
LI, Xin
DENG, Yang
BING, Lidong
LAM, Wai
author_facet ZHANG, Wenxuan
LI, Xin
DENG, Yang
BING, Lidong
LAM, Wai
author_sort ZHANG, Wenxuan
title Towards generative aspect-based sentiment analysis
title_short Towards generative aspect-based sentiment analysis
title_full Towards generative aspect-based sentiment analysis
title_fullStr Towards generative aspect-based sentiment analysis
title_full_unstemmed Towards generative aspect-based sentiment analysis
title_sort towards generative aspect-based sentiment analysis
publisher Institutional Knowledge at Singapore Management University
publishDate 2021
url https://ink.library.smu.edu.sg/sis_research/9112
https://ink.library.smu.edu.sg/context/sis_research/article/10115/viewcontent/2021.acl_short.64.pdf
_version_ 1814047744758644736