MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answering
Autor: | Gu, Nianlong, Gao, Yingqiang, Hahnloser, Richard H. R. |
---|---|
Rok vydání: | 2023 |
Předmět: | |
Druh dokumentu: | Working Paper |
Popis: | 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. Comment: 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 |
Databáze: | arXiv |
Externí odkaz: |