MARE: Multi-Aspect Rationale Extractor on Unsupervised Rationale Extraction

Han Jiang, Junwen Duan, Zhe Qu, Jianxin Wang

Abstract
Unsupervised rationale extraction aims to extract text snippets to support model predictions without explicit rationale annotation.Researchers have made many efforts to solve this task. Previous works often encode each aspect independently, which may limit their ability to capture meaningful internal correlations between aspects. While there has been significant work on mitigating spurious correlations, our approach focuses on leveraging the beneficial internal correlations to improve multi-aspect rationale extraction. In this paper, we propose a Multi-Aspect Rationale Extractor (MARE) to explain and predict multiple aspects simultaneously. Concretely, we propose a Multi-Aspect Multi-Head Attention (MAMHA) mechanism based on hard deletion to encode multiple text chunks simultaneously. Furthermore, multiple special tokens are prepended in front of the text with each corresponding to one certain aspect. Finally, multi-task training is deployed to reduce the training overhead. Experimental results on two unsupervised rationale extraction benchmarks show that MARE achieves state-of-the-art performance. Ablation studies further demonstrate the effectiveness of our method. Our codes have been available at https://github.com/CSU-NLP-Group/MARE.
Anthology ID:
2024.emnlp-main.655
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11734–11745
Language:
URL:
https://aclanthology.org/2024.emnlp-main.655
DOI:
10.18653/v1/2024.emnlp-main.655
Bibkey:
Cite (ACL):
Han Jiang, Junwen Duan, Zhe Qu, and Jianxin Wang. 2024. MARE: Multi-Aspect Rationale Extractor on Unsupervised Rationale Extraction. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 11734–11745, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
MARE: Multi-Aspect Rationale Extractor on Unsupervised Rationale Extraction (Jiang et al., EMNLP 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2024.emnlp-main.655.pdf
PDF Search