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

arXiv: https://arxiv.org/abs/2005.01898 · HTML: https://mlsanity.com/paper/2005.01898/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2020.

## Built on by (most cited first, 17 of 17)

- [NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned](https://mlsanity.com/paper/2101.00133/) (2021)
- [UnitedQA: A Hybrid Approach for Open Domain Question Answering](https://mlsanity.com/paper/2101.00178/) (2021)
- [R2-D2: A Modular Baseline for Open-Domain Question Answering](https://mlsanity.com/paper/2109.03502/) (2021)
- [Open Domain Question Answering with A Unified Knowledge Interface](https://mlsanity.com/paper/2110.08417/) (2021)
- [Introspective Distillation for Robust Question Answering](https://mlsanity.com/paper/2111.01026/) (2021)
- [It is AI's Turn to Ask Humans a Question: Question-Answer Pair Generation for Children's Story Books](https://mlsanity.com/paper/2109.03423/) (2021)
- [DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization](https://mlsanity.com/paper/2109.04673/) (2021)
- [Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study](https://mlsanity.com/paper/2106.03826/) (2021)
- [Grow-and-Clip: Informative-yet-Concise Evidence Distillation for Answer Explanation](https://mlsanity.com/paper/2201.05088/) (2022)
- [ReadTwice: Reading Very Large Documents with Memories](https://mlsanity.com/paper/2105.04241/) (2021)
- [Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge](https://mlsanity.com/paper/2210.12338/) (2022)
- [Pruning the Index Contents for Memory Efficient Open-Domain QA](https://mlsanity.com/paper/2102.10697/) (2021)
- [Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation](https://mlsanity.com/paper/2110.04889/) (2021)
- [FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering](https://mlsanity.com/paper/2211.10147/) (2022)
- [CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations](https://mlsanity.com/paper/2210.02223/) (2022)
- [FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection](https://mlsanity.com/paper/2408.06333/) (2024)
- [MRCLens: an MRC Dataset Bias Detection Toolkit](https://mlsanity.com/paper/2207.08943/) (2022)

## 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.