Adapting BERT for target-oriented multimodal sentiment classification

As an important task in Sentiment Analysis, Target-oriented Sentiment Classification (TSC) aims to identify sentiment polarities over each opinion target in a sentence. However, existing approaches to this task primarily rely on the textual content, but ignoring the other increasingly popular multim...

Full description

Saved in:
Bibliographic Details
Main Authors: YU, Jianfei, JIANG, Jing
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2019
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/4441
https://ink.library.smu.edu.sg/context/sis_research/article/5444/viewcontent/9._Adapting_BERT_for_Target_Oriented_Multimodal_Sentiment_Classification__IJCAI2019_.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-5444
record_format dspace
spelling sg-smu-ink.sis_research-54442020-04-08T05:49:20Z Adapting BERT for target-oriented multimodal sentiment classification YU, Jianfei JIANG, Jing As an important task in Sentiment Analysis, Target-oriented Sentiment Classification (TSC) aims to identify sentiment polarities over each opinion target in a sentence. However, existing approaches to this task primarily rely on the textual content, but ignoring the other increasingly popular multimodal data sources (e.g., images), which can enhance the robustness of these text-based models. Motivated by this observation and inspired by the recently proposed BERT architecture, we study Target-oriented Multimodal Sentiment Classification (TMSC) and propose a multimodal BERT architecture. To model intra-modality dynamics, we first apply BERT to obtain target-sensitive textual representations. We then borrow the idea from self-attention and design a target attention mechanism to perform target-image matching to derive target-sensitive visual representations. To model inter-modality dynamics, we further propose to stack a set of self-attention layers to capture multimodal interactions. Experimental results show that our model can outperform several highly competitive approaches for TSC and TMSC. 2019-08-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/4441 info:doi/10.24963/ijcai.2019/751 https://ink.library.smu.edu.sg/context/sis_research/article/5444/viewcontent/9._Adapting_BERT_for_Target_Oriented_Multimodal_Sentiment_Classification__IJCAI2019_.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 Artificial Intelligence and Robotics Databases and Information Systems Numerical Analysis and Scientific Computing
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
Artificial Intelligence and Robotics
Databases and Information Systems
Numerical Analysis and Scientific Computing
spellingShingle Natural Language Processing
Sentiment Analysis and Text Mining
Artificial Intelligence and Robotics
Databases and Information Systems
Numerical Analysis and Scientific Computing
YU, Jianfei
JIANG, Jing
Adapting BERT for target-oriented multimodal sentiment classification
description As an important task in Sentiment Analysis, Target-oriented Sentiment Classification (TSC) aims to identify sentiment polarities over each opinion target in a sentence. However, existing approaches to this task primarily rely on the textual content, but ignoring the other increasingly popular multimodal data sources (e.g., images), which can enhance the robustness of these text-based models. Motivated by this observation and inspired by the recently proposed BERT architecture, we study Target-oriented Multimodal Sentiment Classification (TMSC) and propose a multimodal BERT architecture. To model intra-modality dynamics, we first apply BERT to obtain target-sensitive textual representations. We then borrow the idea from self-attention and design a target attention mechanism to perform target-image matching to derive target-sensitive visual representations. To model inter-modality dynamics, we further propose to stack a set of self-attention layers to capture multimodal interactions. Experimental results show that our model can outperform several highly competitive approaches for TSC and TMSC.
format text
author YU, Jianfei
JIANG, Jing
author_facet YU, Jianfei
JIANG, Jing
author_sort YU, Jianfei
title Adapting BERT for target-oriented multimodal sentiment classification
title_short Adapting BERT for target-oriented multimodal sentiment classification
title_full Adapting BERT for target-oriented multimodal sentiment classification
title_fullStr Adapting BERT for target-oriented multimodal sentiment classification
title_full_unstemmed Adapting BERT for target-oriented multimodal sentiment classification
title_sort adapting bert for target-oriented multimodal sentiment classification
publisher Institutional Knowledge at Singapore Management University
publishDate 2019
url https://ink.library.smu.edu.sg/sis_research/4441
https://ink.library.smu.edu.sg/context/sis_research/article/5444/viewcontent/9._Adapting_BERT_for_Target_Oriented_Multimodal_Sentiment_Classification__IJCAI2019_.pdf
_version_ 1770574838796124160