StyLEx: Explaining Style Using Human Lexical Annotations

Shirley Anugrah Hayati, Kyumin Park, Dheeraj Rajagopal, Lyle Ungar, Dongyeop Kang


Abstract
Large pre-trained language models have achieved impressive results on various style classification tasks, but they often learn spurious domain-specific words to make predictions (Hayati et al., 2021). While human explanation highlights stylistic tokens as important features for this task, we observe that model explanations often do not align with them. To tackle this issue, we introduce StyLEx, a model that learns from human annotated explanations of stylistic features and jointly learns to perform the task and predict these features as model explanations. Our experiments show that StyLEx can provide human like stylistic lexical explanations without sacrificing the performance of sentence-level style prediction on both in-domain and out-of-domain datasets. Explanations from StyLEx show significant improvements in explanation metrics (sufficiency, plausibility) and when evaluated with human annotations. They are also more understandable by human judges compared to the widely-used saliency-based explanation baseline.
Anthology ID:
2023.eacl-main.208
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2843–2856
Language:
URL:
https://aclanthology.org/2023.eacl-main.208
DOI:
Bibkey:
Cite (ACL):
Shirley Anugrah Hayati, Kyumin Park, Dheeraj Rajagopal, Lyle Ungar, and Dongyeop Kang. 2023. StyLEx: Explaining Style Using Human Lexical Annotations. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2843–2856, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
StyLEx: Explaining Style Using Human Lexical Annotations (Hayati et al., EACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/starsem-semeval-split/2023.eacl-main.208.pdf