Abstract
Table Question Answering (TQA) is an important but under-explored task. Most of the existing QA datasets are in unstructured text format and only few of them use tables as the context. To the best of our knowledge, none of TQA datasets exist in the biomedical domain where tables are frequently used to present information. In this paper, we first curate a table question answering dataset, BioTabQA, using 22 templates and the context from a biomedical textbook on differential diagnosis. BioTabQA can not only be used to teach a model how to answer questions from tables but also evaluate how a model generalizes to unseen questions, an important scenario for biomedical applications. To achieve the generalization evaluation, we divide the templates into 17 training and 5 cross-task evaluations. Then, we develop two baselines using single and multi-tasks learning on BioTabQA. Furthermore, we explore instructional learning, a recent technique showing impressive generalizing performance. Experimental results show that our instruction-tuned model outperforms single and multi task baselines on an average by ∼ 23% and ∼ 6% across various evaluation settings, and more importantly, instruction-tuned model outperforms baselines by ∼ 5% on cross-tasks.
Original language | English (US) |
---|---|
Pages (from-to) | 291-304 |
Number of pages | 14 |
Journal | CEUR Workshop Proceedings |
Volume | 3180 |
State | Published - 2022 |
Event | 2022 Conference and Labs of the Evaluation Forum, CLEF 2022 - Duration: Jan 1 2022 → … |
Keywords
- Table question answering
- biomedical question answering
- instruction learning
- prompt learning
ASJC Scopus subject areas
- General Computer Science