mlsanityData to 7 Oct 2026

Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering

arXiv 2005.01898 ↗First posted 5 May 2020cs.CL cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

We address the problem of extractive question answering using document-level distant super-vision, pairing questions and relevant documents with answer strings. We compare previously used probability space and distant super-vision assumptions (assumptions on the correspondence between the weak answer string labels and possible answer mention spans). We show that these assumptions interact, and that different configurations provide complementary benefits. We demonstrate that a multi-objective model can efficiently combine the advantages of multiple assumptions and out-perform the best individual formulation. Our approach outperforms previous state-of-the-art models by 4.3 points in F1 on TriviaQA-Wiki and 1.7 points in Rouge-L on NarrativeQA summaries.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 11; 2022: 5; 2023: 0; 2024: 1.

17 papers.

Sort:

By area:

  1. 2021NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learnedcited by 52
  2. 2021UnitedQA: A Hybrid Approach for Open Domain Question Answeringcited by 42
  3. 2021R2-D2: A Modular Baseline for Open-Domain Question Answeringcited by 37
  4. 2021Open Domain Question Answering with A Unified Knowledge Interfacecited by 32
  5. 2021Introspective Distillation for Robust Question Answeringcited by 25
  6. 2021It is AI's Turn to Ask Humans a Question: Question-Answer Pair Generation for Children's Story Bookscited by 23
  7. 2021DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualizationcited by 21
  8. 2022Grow-and-Clip: Informative-yet-Concise Evidence Distillation for Answer Explanationcited by 16
  9. 2021Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Studycited by 15
  10. 2021ReadTwice: Reading Very Large Documents with Memoriescited by 14
  11. 2022Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledgecited by 14
  12. 2021Pruning the Index Contents for Memory Efficient Open-Domain QAcited by 6
5 more
  1. 2021Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotationcited by 5
  2. 2022FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answeringcited by 5
  3. 2022CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversationscited by 4
  4. 2024FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selectioncited by 2
  5. 2022MRCLens: an MRC Dataset Bias Detection Toolkitcited by 0