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

Citation metadata

Date: Mar. 1, 2021
From: PLoS ONE(Vol. 16, Issue 3)
Publisher: Public Library of Science
Document Type: Report
Length: 6,047 words
Lexile Measure: 1410L

Document controls

Main content

Abstract :

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.

Source Citation

Source Citation   

Gale Document Number: GALE|A653453945