Source-Free Domain Adaptation for Question Answering with Masked Self-training
Open Access
- 4 June 2024
- journal article
- research article
- Published by MIT Press in Transactions of the Association for Computational Linguistics
- Vol. 12, 721-737
Abstract
Previous unsupervised domain adaptation (UDA) methods for question answering (QA) require access to source domain data while fine-tuning theKeywords
This publication has 28 references indexed in Scilit:
- A fast local citation recommendation algorithm scalable to multi-topicsExpert Systems with Applications, 2023
- Dynamically Instance-Guided Adaptation: A Backward-free Approach for Test-Time Domain Adaptive Semantic Segmentation2023
- CliniQG4QA: Generating Diverse Questions for Domain Adaptation of Clinical Question Answering2021
- PERL: Pivot-based Domain Adaptation for Pre-trained Deep Contextualized Embedding ModelsTransactions of the Association for Computational Linguistics, 2020
- Generative adversarial networksCommunications of the ACM, 2020
- Model Adaptation: Unsupervised Domain Adaptation Without Source Data2020
- Unsupervised Domain Adaptation on Reading ComprehensionProceedings of the AAAI Conference on Artificial Intelligence, 2020
- Natural Questions: A Benchmark for Question Answering ResearchTransactions of the Association for Computational Linguistics, 2019
- An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competitionBMC Bioinformatics, 2015
- PhysioBank, PhysioToolkit, and PhysioNetCirculation, 2000