Structural Bias for Aspect Sentiment Triplet Extraction

Chen Zhang, Lei Ren, Fang Ma, Jingang Wang, Wei Wu, Dawei Song


Abstract
Structural bias has recently been exploited for aspect sentiment triplet extraction (ASTE) and led to improved performance. On the other hand, it is recognized that explicitly incorporating structural bias would have a negative impact on efficiency, whereas pretrained language models (PLMs) can already capture implicit structures. Thus, a natural question arises: Is structural bias still a necessity in the context of PLMs? To answer the question, we propose to address the efficiency issues by using an adapter to integrate structural bias in the PLM and using a cheap-to-compute relative position structure in place of the syntactic dependency structure. Benchmarking evaluation is conducted on the SemEval datasets. The results show that our proposed structural adapter is beneficial to PLMs and achieves state-of-the-art performance over a range of strong baselines, yet with a light parameter demand and low latency. Meanwhile, we give rise to the concern that the current evaluation default with data of small scale is under-confident. Consequently, we release a large-scale dataset for ASTE. The results on the new dataset hint that the structural adapter is confidently effective and efficient to a large scale. Overall, we draw the conclusion that structural bias shall still be a necessity even with PLMs.
Anthology ID:
2022.coling-1.585
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:
6736–6745
Language:
URL:
https://aclanthology.org/2022.coling-1.585
DOI:
Bibkey:
Cite (ACL):
Chen Zhang, Lei Ren, Fang Ma, Jingang Wang, Wei Wu, and Dawei Song. 2022. Structural Bias for Aspect Sentiment Triplet Extraction. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6736–6745, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Structural Bias for Aspect Sentiment Triplet Extraction (Zhang et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.585.pdf
Code
 genezc/structbias