Paragraph-based Transformer Pre-training for Multi-Sentence Inference
Luca Di Liello, Siddhant Garg, Luca Soldaini, Alessandro Moschitti
Abstract
Inference tasks such as answer sentence selection (AS2) or fact verification are typically solved by fine-tuning transformer-based models as individual sentence-pair classifiers. Recent studies show that these tasks benefit from modeling dependencies across multiple candidate sentences jointly. In this paper, we first show that popular pre-trained transformers perform poorly when used for fine-tuning on multi-candidate inference tasks. We then propose a new pre-training objective that models the paragraph-level semantics across multiple input sentences. Our evaluation on three AS2 and one fact verification datasets demonstrates the superiority of our pre-training technique over the traditional ones for transformers used as joint models for multi-candidate inference tasks, as well as when used as cross-encoders for sentence-pair formulations of these tasks.
BibTeX
@inproceedings{di-liello-etal-2022-paragraph,
title = "Paragraph-based Transformer Pre-training for Multi-Sentence Inference",
author = "Di Liello, Luca and
Garg, Siddhant and
Soldaini, Luca and
Moschitti, Alessandro",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.181/",
doi = "10.18653/v1/2022.naacl-main.181",
pages = "2521--2531"
}