We introduce MemSum-DQA, an efficient system for document question answering (DQA) that leverages MemSum, a long document extractive summarizer. By prefixing each text block in the parsed document with the provided question and question type, MemSum-DQA selectively extracts text blocks as answers from documents. On full-document answering tasks, this approach yields a 9% improvement in exact match accuracy over prior state-of-the-art baselines. Notably, MemSum-DQA excels in addressing questions related to child-relationship understanding, underscoring the potential of extractive summarization techniques for DQA tasks.
@article{arxiv.2310.06436,
title = {MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answering},
author = {Nianlong Gu and Yingqiang Gao and Richard H. R. Hahnloser},
journal= {arXiv preprint arXiv:2310.06436},
year = {2023}
}
Comments
This paper is the technical research paper of CIKM 2023 DocIU challenges. The authors received the CIKM 2023 DocIU Winner Award, sponsored by Google, Microsoft, and the Centre for data-driven geoscience