# MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answering

arXiv: https://arxiv.org/abs/2310.06436 · HTML: https://mlsanity.com/paper/2310.06436/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 35 references that are in the map.
- First posted on arXiv 10 Oct 2023.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review](https://mlsanity.com/paper/2103.06268/) (2021)
- [DocBank: A Benchmark Dataset for Document Layout Analysis](https://mlsanity.com/paper/2006.01038/) (2020)
- [SciREX: A Challenge Dataset for Document-Level Information Extraction](https://mlsanity.com/paper/2005.00512/) (2020)
- [Question Answering by Reasoning Across Documents with Graph Convolutional Networks](https://mlsanity.com/paper/1808.09920/) (2018)
- [Explaining Relationships Between Scientific Documents](https://mlsanity.com/paper/2002.00317/) (2020)
- [PDFTriage: Question Answering over Long, Structured Documents](https://mlsanity.com/paper/2309.08872/) (2023)
- [PDFVQA: A New Dataset for Real-World VQA on PDF Documents](https://mlsanity.com/paper/2304.06447/) (2023)
- [Keyphrase Generation for Scientific Document Retrieval](https://mlsanity.com/paper/2106.14726/) (2021)
- [Visconde: Multi-document QA with GPT-3 and Neural Reranking](https://mlsanity.com/paper/2212.09656/) (2022)
- [Hierarchical Question Answering for Long Documents](https://mlsanity.com/paper/1611.01839/) (2016)
- [RikiNet: Reading Wikipedia Pages for Natural Question Answering](https://mlsanity.com/paper/2004.14560/) (2020)
- [Representations for Question Answering from Documents with Tables and Text](https://mlsanity.com/paper/2101.10573/) (2021)
- [MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes](https://mlsanity.com/paper/2107.08929/) (2021)
- [Local Citation Recommendation with Hierarchical-Attention Text Encoder and SciBERT-based Reranking](https://mlsanity.com/paper/2112.01206/) (2021)
- [Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network](https://mlsanity.com/paper/2210.05499/) (2022)
- [Legal Extractive Summarization of U.S. Court Opinions](https://mlsanity.com/paper/2305.08428/) (2023)
- [AttenWalker: Unsupervised Long-Document Question Answering via Attention-based Graph Walking](https://mlsanity.com/paper/2305.02235/) (2023)
- [DoSA : A System to Accelerate Annotations on Business Documents with Human-in-the-Loop](https://mlsanity.com/paper/2211.04934/) (2022)

## Built on by (most cited first, 1 of 1)

- [AutothinkRAG: Complexity-Aware Control of Retrieval-Augmented Reasoning for Image-Text Interaction](https://mlsanity.com/paper/2603.05551/) (2026)

## Abstract (arXiv)

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.