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

arXiv: https://arxiv.org/abs/2210.02621 · HTML: https://mlsanity.com/paper/2210.02621/

## 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 (most cited first, 30 of 35)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [Understanding Neural Networks through Representation Erasure](https://mlsanity.com/paper/1612.08220/) (2016)
- [Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting](https://mlsanity.com/paper/1805.11080/) (2018)
- [DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension](https://mlsanity.com/paper/1902.00164/) (2019)
- [Pathologies of Neural Models Make Interpretations Difficult](https://mlsanity.com/paper/1804.07781/) (2018)
- [Bilateral Multi-Perspective Matching for Natural Language Sentences](https://mlsanity.com/paper/1702.03814/) (2017)
- [Multi-hop Reading Comprehension through Question Decomposition and Rescoring](https://mlsanity.com/paper/1906.02916/) (2019)
- [Retrospective Reader for Machine Reading Comprehension](https://mlsanity.com/paper/2001.09694/) (2020)
- [Investigating Prior Knowledge for Challenging Chinese Machine Reading Comprehension](https://mlsanity.com/paper/1904.09679/) (2019)
- [Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents](https://mlsanity.com/paper/2110.10150/) (2021)
- [How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking](https://mlsanity.com/paper/2004.14992/) (2020)
- [UKP-Athene: Multi-Sentence Textual Entailment for Claim Verification](https://mlsanity.com/paper/1809.01479/) (2018)
- [Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents](https://mlsanity.com/paper/1911.00484/) (2019)
- [Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction](https://mlsanity.com/paper/1905.08511/) (2019)
- [Multi-granularity hierarchical attention fusion networks for reading comprehension and question answering](https://mlsanity.com/paper/1811.11934/) (2018)
- [Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion](https://mlsanity.com/paper/2106.08657/) (2021)
- [Efficient and Robust Question Answering from Minimal Context over Documents](https://mlsanity.com/paper/1805.08092/) (2018)
- [Hierarchical Question Answering for Long Documents](https://mlsanity.com/paper/1611.01839/) (2016)
- [ReCO: A Large Scale Chinese Reading Comprehension Dataset on Opinion](https://mlsanity.com/paper/2006.12146/) (2020)
- [Weakly- and Semi-supervised Evidence Extraction](https://mlsanity.com/paper/2011.01459/) (2020)
- [Evidence Sentence Extraction for Machine Reading Comprehension](https://mlsanity.com/paper/1902.08852/) (2019)
- [Option Comparison Network for Multiple-choice Reading Comprehension](https://mlsanity.com/paper/1903.03033/) (2019)

## 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.