Making Better Use of Training Corpus: Retrieval-based Aspect Sentiment Triplet Extraction via Label Interpolation

Guoxin Yu, Lemao Liu, Haiyun Jiang, Shuming Shi, Xiang Ao

Abstract
In this paper, we aim to adapt the idea of retrieval-based neural approaches to the Aspect Sentiment Triplet Extraction (ASTE) task. Different from previous studies retrieving semantic similar neighbors, the ASTE task has its specialized challenges when adapting, i.e., the purpose includes predicting the sentiment polarity and it is usually aspect-dependent. Semantic similar neighbors with different polarities will be infeasible even counterproductive. To tackle this issue, we propose a retrieval-based neural ASTE approach, named RLI (Retrieval-based Aspect Sentiment Triplet Extraction via Label Interpolation), which exploits the label information of neighbors. Given an aspect-opinion term pair, we retrieve semantic similar triplets from the training corpus and interpolate their label information into the augmented representation of the target pair. The retriever is jointly trained with the whole ASTE framework, and neighbors with both similar semantics and sentiments can be recalled with the aid of this distant supervision. In addition, we design a simple yet effective pre-train method for the retriever that implicitly encodes the label similarities. Extensive experiments and analysis on two widely-used benchmarks show that the proposed model establishes a new state-of-the-art on ASTE.
Anthology ID:
2023.findings-acl.303
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4914–4927
Language:
URL:
https://aclanthology.org/2023.findings-acl.303
DOI:
10.18653/v1/2023.findings-acl.303
Bibkey:
Cite (ACL):
Guoxin Yu, Lemao Liu, Haiyun Jiang, Shuming Shi, and Xiang Ao. 2023. Making Better Use of Training Corpus: Retrieval-based Aspect Sentiment Triplet Extraction via Label Interpolation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 4914–4927, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Making Better Use of Training Corpus: Retrieval-based Aspect Sentiment Triplet Extraction via Label Interpolation (Yu et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.findings-acl.303.pdf
PDF Search