mlsanityData to 14 Oct 2026

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

arXiv 2310.06436 ↗First posted 10 Oct 2023cs.CLcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper 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

27 of 35 references.

References · 27

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  3. 2020Longformer: The Long-Document Transformercited by 3,413
  4. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  5. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,553
  6. 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,296
  7. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,230
  8. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 740
  9. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  10. 2021CUAD: An Expert-Annotated NLP Dataset for Legal Contract Reviewcited by 236
  11. 2020DocBank: A Benchmark Dataset for Document Layout Analysiscited by 153
  12. 2020SciREX: A Challenge Dataset for Document-Level Information Extractioncited by 113
15 more
  1. 2018Question Answering by Reasoning Across Documents with Graph Convolutional Networkscited by 56
  2. 2020Explaining Relationships Between Scientific Documentscited by 35
  3. 2023PDFTriage: Question Answering over Long, Structured Documentscited by 29
  4. 2023PDFVQA: A New Dataset for Real-World VQA on PDF Documentscited by 28
  5. 2021Keyphrase Generation for Scientific Document Retrievalcited by 23
  6. 2022Visconde: Multi-document QA with GPT-3 and Neural Rerankingcited by 23
  7. 2016Hierarchical Question Answering for Long Documentscited by 21
  8. 2020RikiNet: Reading Wikipedia Pages for Natural Question Answeringcited by 21
  9. 2021Representations for Question Answering from Documents with Tables and Textcited by 21
  10. 2021MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processescited by 19
  11. 2021Local Citation Recommendation with Hierarchical-Attention Text Encoder and SciBERT-based Rerankingcited by 19
  12. 2022Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Networkcited by 9
  13. 2023Legal Extractive Summarization of U.S. Court Opinionscited by 9
  14. 2023AttenWalker: Unsupervised Long-Document Question Answering via Attention-based Graph Walkingcited by 3
  15. 2022DoSA : A System to Accelerate Annotations on Business Documents with Human-in-the-Loopcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026AutothinkRAG: Complexity-Aware Control of Retrieval-Augmented Reasoning for Image-Text Interactioncited by 0