mlsanityData to 14 Oct 2026

U3E: Unsupervised and Erasure-based Evidence Extraction for Machine Reading Comprehension

arXiv 2210.02621 ↗First posted 6 Oct 2022cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

More tasks in Machine Reading Comprehension(MRC) require, in addition to answer prediction, the extraction of evidence sentences that support the answer. However, the annotation of supporting evidence sentences is usually time-consuming and labor-intensive. In this paper, to address this issue and considering that most of the existing extraction methods are semi-supervised, we propose an unsupervised evidence extraction method (U3E). U3E takes the changes after sentence-level feature erasure in the document as input, simulating the decline in problem-solving ability caused by human memory decline. In order to make selections on the basis of fully understanding the semantics of the original text, we also propose metrics to quickly select the optimal memory model for this input changes. To compare U3E with typical evidence extraction methods and investigate its effectiveness in evidence extraction, we conduct experiments on different datasets. Experimental results show that U3E is simple but effective, not only extracting evidence more accurately, but also significantly improving model performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 51 references that are in the map. First posted on arXiv 6 Oct 2022.

Builds on

35 of 51 references.

References · 35

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,183
  6. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  7. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 903
  8. 2017RACE: Large-scale ReAding Comprehension Dataset From Examinationscited by 861
  9. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 571
  10. 2016Understanding Neural Networks through Representation Erasurecited by 224
  11. 2018Fast Abstractive Summarization with Reinforce-Selected Sentence Rewritingcited by 158
  12. 2019DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehensioncited by 156
23 more
  1. 2018Pathologies of Neural Models Make Interpretations Difficultcited by 140
  2. 2017Bilateral Multi-Perspective Matching for Natural Language Sentencescited by 121
  3. 2019Multi-hop Reading Comprehension through Question Decomposition and Rescoringcited by 119
  4. 2020Retrospective Reader for Machine Reading Comprehensioncited by 86
  5. 2019Investigating Prior Knowledge for Challenging Chinese Machine Reading Comprehensioncited by 81
  6. 2021Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documentscited by 65
  7. 2020How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Maskingcited by 63
  8. 2018UKP-Athene: Multi-Sentence Textual Entailment for Claim Verificationcited by 60
  9. 2019Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documentscited by 57
  10. 2019Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extractioncited by 39
  11. 2018Multi-granularity hierarchical attention fusion networks for reading comprehension and question answeringcited by 28
  12. 2021Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusioncited by 28
  13. 2018Efficient and Robust Question Answering from Minimal Context over Documentscited by 26
  14. 2016Hierarchical Question Answering for Long Documentscited by 21
  15. 2020ReCO: A Large Scale Chinese Reading Comprehension Dataset on Opinioncited by 16
  16. 2020Weakly- and Semi-supervised Evidence Extractioncited by 16
  17. 2019Evidence Sentence Extraction for Machine Reading Comprehensioncited by 14
  18. 2019Option Comparison Network for Multiple-choice Reading Comprehensioncited by 14
  19. 2021Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehensioncited by 10
  20. 2020A Self-Training Method for Machine Reading Comprehension with Soft Evidence Extractioncited by 9
  21. 2020DUMA: Reading Comprehension with Transposition Thinkingcited by 8
  22. 2021ExpMRC: Explainability Evaluation for Machine Reading Comprehensioncited by 4
  23. 2021Extract, Integrate, Compete: Towards Verification Style Reading Comprehensioncited by 3

Built on by

Not cited yet.