A weakly supervised textual entailment approach to zero-shot text classification
Marc Pàmies, Joan Llop, Francesco Multari, Nicolau Duran-Silva, César Parra-Rojas, Aitor Gonzalez-Agirre, Francesco Alessandro Massucci, Marta Villegas
Abstract
Zero-shot text classification is a widely studied task that deals with a lack of annotated data. The most common approach is to reformulate it as a textual entailment problem, enabling classification into unseen classes. This work explores an effective approach that trains on a weakly supervised dataset generated from traditional classification data. We empirically study the relation between the performance of the entailment task, which is used as a proxy, and the target zero-shot text classification task. Our findings reveal that there is no linear correlation between both tasks, to the extent that it can be detrimental to lengthen the fine-tuning process even when the model is still learning, and propose a straightforward method to stop training on time. As a proof of concept, we introduce a domain-specific zero-shot text classifier that was trained on Microsoft Academic Graph data. The model, called SCIroShot, achieves state-of-the-art performance in the scientific domain and competitive results in other areas. Both the model and evaluation benchmark are publicly available on HuggingFace and GitHub.- Anthology ID:
- 2023.eacl-main.22
- Volume:
- Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Andreas Vlachos, Isabelle Augenstein
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 286–296
- Language:
- URL:
- https://aclanthology.org/2023.eacl-main.22
- DOI:
- 10.18653/v1/2023.eacl-main.22
- Cite (ACL):
- Marc Pàmies, Joan Llop, Francesco Multari, Nicolau Duran-Silva, César Parra-Rojas, Aitor Gonzalez-Agirre, Francesco Alessandro Massucci, and Marta Villegas. 2023. A weakly supervised textual entailment approach to zero-shot text classification. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 286–296, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- A weakly supervised textual entailment approach to zero-shot text classification (Pàmies et al., EACL 2023)
- PDF:
- https://preview.aclanthology.org/revert-3132-ingestion-checklist/2023.eacl-main.22.pdf