MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answering
Metadata only
Datum
2023-10-10Typ
- Working Paper
ETH Bibliographie
yes
Altmetrics
Abstract
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. Mehr anzeigen
Publikationsstatus
publishedZeitschrift / Serie
arXivSeiten / Artikelnummer
Verlag
Cornell UniversityThema
Computation and Language (cs.CL); FOS: Computer and information sciences; Document understanding; Question answeringOrganisationseinheit
03774 - Hahnloser, Richard H.R. / Hahnloser, Richard H.R.
ETH Bibliographie
yes
Altmetrics