Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora

Flor Miriam Plaza-del-Arco, María-Teresa Martín-Valdivia, Roman Klinger


Abstract
Within textual emotion classification, the set of relevant labels depends on the domain and application scenario and might not be known at the time of model development. This conflicts with the classical paradigm of supervised learning in which the labels need to be predefined. A solution to obtain a model with a flexible set of labels is to use the paradigm of zero-shot learning as a natural language inference task, which in addition adds the advantage of not needing any labeled training data. This raises the question how to prompt a natural language inference model for zero-shot learning emotion classification. Options for prompt formulations include the emotion name anger alone or the statement “This text expresses anger”. With this paper, we analyze how sensitive a natural language inference-based zero-shot-learning classifier is to such changes to the prompt under consideration of the corpus: How carefully does the prompt need to be selected? We perform experiments on an established set of emotion datasets presenting different language registers according to different sources (tweets, events, blogs) with three natural language inference models and show that indeed the choice of a particular prompt formulation needs to fit to the corpus. We show that this challenge can be tackled with combinations of multiple prompts. Such ensemble is more robust across corpora than individual prompts and shows nearly the same performance as the individual best prompt for a particular corpus.
Anthology ID:
2022.coling-1.592
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Editors:
Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony Kyungil Lee, Enrico Santus, Francis Bond, Seung-Hoon Na
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
6805–6817
Language:
URL:
https://aclanthology.org/2022.coling-1.592
DOI:
Bibkey:
Cite (ACL):
Flor Miriam Plaza-del-Arco, María-Teresa Martín-Valdivia, and Roman Klinger. 2022. Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6805–6817, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora (Plaza-del-Arco et al., COLING 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp22-frontmatter/2022.coling-1.592.pdf
Code
 fmplaza/zsl_nli_emotion_prompts