Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection
Luca Di Liello, Siddhant Garg, Luca Soldaini, Alessandro Moschitti
Abstract
An important task for designing QA systems is answer sentence selection (AS2): selecting the sentence containing (or constituting) the answer to a question from a set of retrieved relevant documents. In this paper, we propose three novel sentence-level transformer pre-training objectives that incorporate paragraph-level semantics within and across documents, to improve the performance of transformers for AS2, and mitigate the requirement of large labeled datasets. Specifically, the model is tasked to predict whether: (i) two sentences are extracted from the same paragraph, (ii) a given sentence is extracted from a given paragraph, and (iii) two paragraphs are extracted from the same document. Our experiments on three public and one industrial AS2 datasets demonstrate the empirical superiority of our pre-trained transformers over baseline models such as RoBERTa and ELECTRA for AS2.- Anthology ID:
- 2022.emnlp-main.810
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 11806–11816
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.810
- DOI:
- 10.18653/v1/2022.emnlp-main.810
- Cite (ACL):
- Luca Di Liello, Siddhant Garg, Luca Soldaini, and Alessandro Moschitti. 2022. Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11806–11816, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection (Di Liello et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2022.emnlp-main.810.pdf