# MCR-Net: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension

arXiv: https://arxiv.org/abs/2103.04567 · HTML: https://mlsanity.com/paper/2103.04567/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 23 references that are in the map.
- First posted on arXiv 8 Mar 2021.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [Bidirectional Attention Flow for Machine Comprehension](https://mlsanity.com/paper/1611.01603/) (2016)
- [Simple and Effective Multi-Paragraph Reading Comprehension](https://mlsanity.com/paper/1710.10723/) (2017)
- [DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications](https://mlsanity.com/paper/1711.05073/) (2017)
- [SG-Net: Syntax-Guided Machine Reading Comprehension](https://mlsanity.com/paper/1908.05147/) (2019)
- [Machine Comprehension Using Match-LSTM and Answer Pointer](https://mlsanity.com/paper/1608.07905/) (2016)
- [Leveraging Knowledge Bases in LSTMs for Improving Machine Reading](https://mlsanity.com/paper/1902.09091/) (2019)
- [Read + Verify: Machine Reading Comprehension with Unanswerable Questions](https://mlsanity.com/paper/1808.05759/) (2018)
- [Stochastic Answer Networks for Machine Reading Comprehension](https://mlsanity.com/paper/1712.03556/) (2017)
- [Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification](https://mlsanity.com/paper/1805.02220/) (2018)
- [A Deep Cascade Model for Multi-Document Reading Comprehension](https://mlsanity.com/paper/1811.11374/) (2018)
- [U-Net: Machine Reading Comprehension with Unanswerable Questions](https://mlsanity.com/paper/1810.06638/) (2018)

## Built on by (most cited first, 2 of 2)

- [Modeling Intention, Emotion and External World in Dialogue Systems](https://mlsanity.com/paper/2202.06476/) (2022)
- [Relational Surrogate Loss Learning](https://mlsanity.com/paper/2202.13197/) (2022)

## Abstract (arXiv)

Question answering systems usually use keyword searches to retrieve potential passages related to a question, and then extract the answer from passages with the machine reading comprehension methods. However, many questions tend to be unanswerable in the real world. In this case, it is significant and challenging how the model determines when no answer is supported by the passage and abstains from answering. Most of the existing systems design a simple classifier to determine answerability implicitly without explicitly modeling mutual interaction and relation between the question and passage, leading to the poor performance for determining the unanswerable questions. To tackle this problem, we propose a Multi-Step Co-Interactive Relation Network (MCR-Net) to explicitly model the mutual interaction and locate key clues from coarse to fine by introducing a co-interactive relation module. The co-interactive relation module contains a stack of interaction and fusion blocks to continuously integrate and fuse history-guided and current-query-guided clues in an explicit way. Experiments on the SQuAD 2.0 and DuReader datasets show that our model achieves a remarkable improvement, outperforming the BERT-style baselines in literature. Visualization analysis also verifies the importance of the mutual interaction between the question and passage.