ZHIXIAOBAO at SemEval-2022 Task 10: Apporoaching Structured Sentiment with Graph Parsing

Yangkun Lin, Chen Liang, Jing Xu, Chong Yang, Yongliang Wang


Abstract
This paper presents our submission to task 10, Structured Sentiment Analysis of the SemEval 2022 competition. The task aims to extract all elements of the fine-grained sentiment in a text. We cast structured sentiment analysis to the prediction of the sentiment graphs following (Barnes et al., 2021), where nodes are spans of sentiment holders, targets and expressions, and directed edges denote the relation types between them. Our approach closely follows that of semantic dependency parsing (Dozat and Manning, 2018). The difference is that we use pre-trained language models (e.g., BERT and RoBERTa) as text encoder to solve the problem of limited annotated data. Additionally, we make improvements on the computation of cross attention and present the suffix masking technique to make further performance improvement. Substantially, our model achieved the Top-1 average Sentiment Graph F1 score on seven datasets in five different languages in the monolingual subtask.
Anthology ID:
2022.semeval-1.187
Volume:
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
SemEval
SIGs:
SIGLEX | SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
1343–1348
Language:
URL:
https://aclanthology.org/2022.semeval-1.187
DOI:
10.18653/v1/2022.semeval-1.187
Bibkey:
Cite (ACL):
Yangkun Lin, Chen Liang, Jing Xu, Chong Yang, and Yongliang Wang. 2022. ZHIXIAOBAO at SemEval-2022 Task 10: Apporoaching Structured Sentiment with Graph Parsing. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1343–1348, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
ZHIXIAOBAO at SemEval-2022 Task 10: Apporoaching Structured Sentiment with Graph Parsing (Lin et al., SemEval 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.semeval-1.187.pdf
Video:
 https://preview.aclanthology.org/ingestion-script-update/2022.semeval-1.187.mp4
Data
MPQA Opinion CorpusNoReC_fine