Effective Token Graph Modeling using a Novel Labeling Strategy for Structured Sentiment Analysis

Wenxuan Shi, Fei Li, Jingye Li, Hao Fei, Donghong Ji


Abstract
The state-of-the-art model for structured sentiment analysis casts the task as a dependency parsing problem, which has some limitations: (1) The label proportions for span prediction and span relation prediction are imbalanced. (2) The span lengths of sentiment tuple components may be very large in this task, which will further exacerbates the imbalance problem. (3) Two nodes in a dependency graph cannot have multiple arcs, therefore some overlapped sentiment tuples cannot be recognized. In this work, we propose nichetargeting solutions for these issues. First, we introduce a novel labeling strategy, which contains two sets of token pair labels, namely essential label set and whole label set. The essential label set consists of the basic labels for this task, which are relatively balanced and applied in the prediction layer. The whole label set includes rich labels to help our model capture various token relations, which are applied in the hidden layer to softly influence our model. Moreover, we also propose an effective model to well collaborate with our labeling strategy, which is equipped with the graph attention networks to iteratively refine token representations, and the adaptive multi-label classifier to dynamically predict multiple relations between token pairs. We perform extensive experiments on 5 benchmark datasets in four languages. Experimental results show that our model outperforms previous SOTA models by a large margin.
Anthology ID:
2022.acl-long.291
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4232–4241
Language:
URL:
https://aclanthology.org/2022.acl-long.291
DOI:
10.18653/v1/2022.acl-long.291
Bibkey:
Cite (ACL):
Wenxuan Shi, Fei Li, Jingye Li, Hao Fei, and Donghong Ji. 2022. Effective Token Graph Modeling using a Novel Labeling Strategy for Structured Sentiment Analysis. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4232–4241, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Effective Token Graph Modeling using a Novel Labeling Strategy for Structured Sentiment Analysis (Shi et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.291.pdf
Code
 xgswlg/tgls
Data
MPQA Opinion CorpusNoReC_fine