English

A Multi-task Learning Framework for Opinion Triplet Extraction

Computation and Language 2020-11-03 v2

Abstract

The state-of-the-art Aspect-based Sentiment Analysis (ABSA) approaches are mainly based on either detecting aspect terms and their corresponding sentiment polarities, or co-extracting aspect and opinion terms. However, the extraction of aspect-sentiment pairs lacks opinion terms as a reference, while co-extraction of aspect and opinion terms would not lead to meaningful pairs without determining their sentiment dependencies. To address the issue, we present a novel view of ABSA as an opinion triplet extraction task, and propose a multi-task learning framework to jointly extract aspect terms and opinion terms, and simultaneously parses sentiment dependencies between them with a biaffine scorer. At inference phase, the extraction of triplets is facilitated by a triplet decoding method based on the above outputs. We evaluate the proposed framework on four SemEval benchmarks for ASBA. The results demonstrate that our approach significantly outperforms a range of strong baselines and state-of-the-art approaches.

Keywords

Cite

@article{arxiv.2010.01512,
  title  = {A Multi-task Learning Framework for Opinion Triplet Extraction},
  author = {Chen Zhang and Qiuchi Li and Dawei Song and Benyou Wang},
  journal= {arXiv preprint arXiv:2010.01512},
  year   = {2020}
}

Comments

10 pages, 4 figures, 3 tables, accepted to EMNLP 2020 Findings. Repo: https://github.com/GeneZC/OTE-MTL

R2 v1 2026-06-23T19:00:37.065Z