Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answering (2310.06436v1)

Published 10 Oct 2023 in cs.CL

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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (34)
  1. Development of an enterprise-grade contract understanding system. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers. 222–229.
  2. Legal Extractive Summarization of U.S. Court Opinions. arXiv:2305.08428 [cs.CL]
  3. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150 (2020).
  4. Keyphrase Generation for Scientific Document Retrieval. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 1118–1126.
  5. Extending Context Window of Large Language Models via Positional Interpolation. arXiv:2306.15595 [cs.CL]
  6. Coarse-to-fine question answering for long documents. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 209–220.
  7. Question Answering by Reasoning Across Documents with Graph Convolutional Networks. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2306–2317.
  8. PDFVQA: A New Dataset for Real-World VQA on PDF Documents. arXiv preprint arXiv:2304.06447 (2023).
  9. Precise zero-shot dense retrieval without relevance labels. arXiv preprint arXiv:2212.10496 (2022).
  10. Do Discourse Indicators Reflect the Main Arguments in Scientific Papers?. In Proceedings of the 9th Workshop on Argument Mining. University of Zurich, 34–50.
  11. MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 6507–6522.
  12. Local citation recommendation with hierarchical-attention text encoder and scibert-based reranking. In European Conference on Information Retrieval. Springer, 274–288.
  13. Cuad: An expert-annotated nlp dataset for legal contract review. arXiv preprint arXiv:2103.06268 (2021).
  14. SciREX: A Challenge Dataset for Document-Level Information Extraction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 7506–7516.
  15. ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision. In International Conference on Machine Learning. https://api.semanticscholar.org/CorpusID:231839613
  16. VisualBERT: A Simple and Performant Baseline for Vision and Language. arXiv:1908.03557 [cs.CV]
  17. DocBank: A Benchmark Dataset for Document Layout Analysis. In Proceedings of the 28th International Conference on Computational Linguistics. 949–960.
  18. RikiNet: Reading Wikipedia Pages for Natural Question Answering. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 6762–6771.
  19. Explaining Relationships Between Scientific Documents. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2130–2144.
  20. An Open Source Contractual Language Understanding Application Using Machine Learning. In Proceedings of the First Workshop on Language Technology and Resources for a Fair, Inclusive, and Safe Society within the 13th Language Resources and Evaluation Conference. 42–50.
  21. AttenWalker: Unsupervised Long-Document Question Answering via Attention-based Graph Walking. arXiv preprint arXiv:2305.02235 (2023).
  22. Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 5036–5047.
  23. Mathias Parisot and Jakub Zavrel. 2022. Multi-objective Representation Learning for Scientific Document Retrieval. In Proceedings of the Third Workshop on Scholarly Document Processing. 80–88.
  24. Visconde: Multi-document QA with GPT-3 and Neural Reranking. In European Conference on Information Retrieval. Springer, 534–543.
  25. Know What You Don’t Know: Unanswerable Questions for SQuAD. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 784–789.
  26. SQuAD: 100,000+ Questions for Machine Comprehension of Text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. 2383–2392.
  27. PDFTriage: Question Answering over Long, Structured Documents. arXiv preprint arXiv:2309.08872 (2023).
  28. End-to-end extraction of structured information from business documents with pointer-generator networks. In Proceedings of the fourth workshop on structured prediction for NLP. 43–52.
  29. DoSA: A System to Accelerate Annotations on Business Documents with Human-in-the-Loop. In Proceedings of the Fourth Workshop on Data Science with Human-in-the-Loop (Language Advances). 23–27.
  30. Hao Tan and Mohit Bansal. 2019. LXMERT: Learning Cross-Modality Encoder Representations from Transformers. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, 5100–5111. https://doi.org/10.18653/v1/D19-1514
  31. LEDGAR: A large-scale multi-label corpus for text classification of legal provisions in contracts. In Proceedings of the Twelfth Language Resources and Evaluation Conference. 1235–1241.
  32. Attention Is All You Need. arXiv:1706.03762 [cs.CL]
  33. Wikiqa: A challenge dataset for open-domain question answering. In Proceedings of the 2015 conference on empirical methods in natural language processing. 2013–2018.
  34. Representations for Question Answering from Documents with Tables and Text. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2895–2906.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Nianlong Gu (10 papers)
  2. Yingqiang Gao (10 papers)
  3. Richard H. R. Hahnloser (17 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now