Self-Supervised Test-Time Learning for Reading Comprehension
Links to Files
Author/Creator
Author/Creator ORCID
Date
Type of Work
Department
Program
Citation of Original Publication
Banerjee, Pratyay, Tejas Gokhale, and Chitta Baral. “Self-Supervised Test-Time Learning for Reading Comprehension.” Edited by Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, and Yichao Zhou. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, June 2021, 1200–1211. https://doi.org/10.18653/v1/2021.naacl-main.95.
Rights
Attribution 4.0 International
Subjects
Abstract
Recent work on unsupervised question answering has shown that models can be trained with procedurally generated question-answer pairs and can achieve performance competitive with supervised methods. In this work, we consider the task of unsupervised reading comprehension and present a method that performs “test-time learning” (TTL) on a given context (text passage), without requiring training on large-scale human-authored datasets containing context-question-answer triplets. This method operates directly on a single test context, uses self-supervision to train models on synthetically generated question-answer pairs, and then infers answers to unseen human-authored questions for this context. Our method achieves accuracies competitive with fully supervised methods and significantly outperforms current unsupervised methods. TTL methods with a smaller model are also competitive with the current state-of-the-art in unsupervised reading comprehension.