Ushio, Asahi, Alva Manchego, Fernando and Camacho-Collados, Jose 2023. An empirical comparison of LM-based question and answer generation methods. Presented at: The 61st Annual Meeting of the Association for Computational Linguistics, 9-14 July 2023. Findings of the Association for Computational Linguistics: ACL 2023. Toronto, Canada: Association for Computational Linguistics, pp. 14262-14272. 10.18653/v1/2023.findings-acl.899 |
Abstract
Question and answer generation (QAG) consists of generating a set of question-answer pairs given a context (e.g. a paragraph). This task has a variety of applications, such as data augmentation for question answering (QA) models, information retrieval and education. In this paper, we establish baselines with three different QAG methodologies that leverage sequence-to-sequence language model (LM) fine-tuning. Experiments show that an end-to-end QAG model, which is computationally light at both training and inference times, is generally robust and outperforms other more convoluted approaches. However, there are differences depending on the underlying generative LM. Finally, our analysis shows that QA models fine-tuned solely on generated question-answer pairs can be competitive when compared to supervised QA models trained on human-labeled data.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Status: | Published |
Schools: | Computer Science & Informatics |
Publisher: | Association for Computational Linguistics |
Last Modified: | 05 Sep 2023 14:15 |
URI: | https://orca.cardiff.ac.uk/id/eprint/161904 |
Actions (repository staff only)
Edit Item |