Multi-Row, Multi-Span Distant Supervision For Table plus Text Question Answering

PROCEEDINGS OF THE 61ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL 2023, VOL 1(2023)

Cited 0|Views3
No score
Abstract
Question answering (QA) over tables and linked text, also called TextTableQA, has witnessed significant research in recent years, as tables are often found embedded in documents along with related text. HybridQA and OTT-QA are the two best-known TextTableQA datasets, with questions that are best answered by combining information from both table cells and linked text passages. A common challenge in both datasets, and TextTableQA in general, is that the training instances include just the question and answer, where the gold answer may match not only multiple table cells across table rows but also multiple text spans within the scope of a table row and its associated text. This leads to a noisy multiinstance training regime. We present MITQA, a transformer-based TextTableQA system that is explicitly designed to cope with distant supervision along both these axes, through a multiinstance loss objective, together with careful curriculum design. Our experiments show that the proposed multi-instance distant supervision approach helps MITQA get sate-of-the-art results beating the existing baselines for both HybridQA and OTT-QA, putting MITQA at the top of HybridQA leaderboard with best EM and F1 scores on a held out test set.
More
Translated text
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined