A message-passing multi-task architecture for the implicit event and polarity detection

Implicit sentiment analysis is a challenging task because the sentiment of a text is expressed in a connotative manner. To tackle this problem, we propose to use textual events as a knowledge source to enrich network representations. To consider task interactions, we present a novel lightweight join...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2021-03, Vol.16 (3), p.e0247704-e0247704
Main Authors: Xiang, Chunli, Zhang, Junchi, Ji, Donghong
Format: Article
Language:English
Subjects:
Analysis
Biology and Life Sciences
Classification
Colleges & universities
Computation
Computational linguistics
Computer and Information Sciences
Computer programs
Data collection
Data mining
Datasets
Drafting software
Editing
Education
Emotions
Engineering
Laboratories
Language processing
Learning
Message passing
Methods
Natural language interfaces
Natural language processing
Neural networks
Performance degradation
Physical Sciences
Polarity
Polarity (Psychology)
Security
Sentiment analysis
Social Sciences
Software
Technology
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Implicit sentiment analysis is a challenging task because the sentiment of a text is expressed in a connotative manner. To tackle this problem, we propose to use textual events as a knowledge source to enrich network representations. To consider task interactions, we present a novel lightweight joint learning paradigm that can pass task-related messages between tasks during training iterations. This is distinct from previous methods that involve multi-task learning by simple parameter sharing. Besides, a human-annotated corpus with implicit sentiment labels and event labels is scarce, which hinders practical applications of deep neural models. Therefore, we further investigate a back-translation approach to expand training instances. Experiment results on a public benchmark demonstrate the effectiveness of both the proposed multi-task architecture and data augmentation strategy.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0247704