A Hierarchical Interactive Network for Joint Span-based Aspect-Sentiment Analysis

Wei Chen, Jinglong Du, Zhao Zhang, Fuzhen Zhuang, Zhongshi He


Abstract
Recently, some span-based methods have achieved encouraging performances for joint aspect-sentiment analysis, which first extract aspects (aspect extraction) by detecting aspect boundaries and then classify the span-level sentiments (sentiment classification). However, most existing approaches either sequentially extract task-specific features, leading to insufficient feature interactions, or they encode aspect features and sentiment features in a parallel manner, implying that feature representation in each task is largely independent of each other except for input sharing. Both of them ignore the internal correlations between the aspect extraction and sentiment classification. To solve this problem, we novelly propose a hierarchical interactive network (HI-ASA) to model two-way interactions between two tasks appropriately, where the hierarchical interactions involve two steps: shallow-level interaction and deep-level interaction. First, we utilize cross-stitch mechanism to combine the different task-specific features selectively as the input to ensure proper two-way interactions. Second, the mutual information technique is applied to mutually constrain learning between two tasks in the output layer, thus the aspect input and the sentiment input are capable of encoding features of the other task via backpropagation. Extensive experiments on three real-world datasets demonstrate HI-ASA’s superiority over baselines.
Anthology ID:
2022.coling-1.611
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
7013–7019
Language:
URL:
https://aclanthology.org/2022.coling-1.611
DOI:
Bibkey:
Cite (ACL):
Wei Chen, Jinglong Du, Zhao Zhang, Fuzhen Zhuang, and Zhongshi He. 2022. A Hierarchical Interactive Network for Joint Span-based Aspect-Sentiment Analysis. In Proceedings of the 29th International Conference on Computational Linguistics, pages 7013–7019, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
A Hierarchical Interactive Network for Joint Span-based Aspect-Sentiment Analysis (Chen et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.611.pdf
Code
 cwei01/hi-asa