# Retrospective Reader for Machine Reading Comprehension

arXiv: https://arxiv.org/abs/2001.09694 · HTML: https://mlsanity.com/paper/2001.09694/

## Key facts

- Cited by 86 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2020.

## Built on by (most cited first, 30 of 86)

- [GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records](https://mlsanity.com/paper/2203.03540/) (2022)
- [TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph](https://mlsanity.com/paper/2104.07302/) (2021)
- [UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training](https://mlsanity.com/paper/2202.12359/) (2022)
- [Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese](https://mlsanity.com/paper/2110.06696/) (2021)
- [From LSAT: The Progress and Challenges of Complex Reasoning](https://mlsanity.com/paper/2108.00648/) (2021)
- [Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering](https://mlsanity.com/paper/2101.00391/) (2021)
- [DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization](https://mlsanity.com/paper/2209.05227/) (2022)
- [Capturing Row and Column Semantics in Transformer Based Question Answering over Tables](https://mlsanity.com/paper/2104.08303/) (2021)
- [UNK-VQA: A Dataset and a Probe into the Abstention Ability of Multi-modal Large Models](https://mlsanity.com/paper/2310.10942/) (2023)
- [Multiple-Choice Question Generation: Towards an Automated Assessment Framework](https://mlsanity.com/paper/2209.11830/) (2022)
- [ReasonBERT: Pre-trained to Reason with Distant Supervision](https://mlsanity.com/paper/2109.04912/) (2021)
- [Structural Pre-training for Dialogue Comprehension](https://mlsanity.com/paper/2105.10956/) (2021)
- [Contrastive Domain Adaptation for Question Answering using Limited Text Corpora](https://mlsanity.com/paper/2108.13854/) (2021)
- [Interpreting Deep Learning Models in Natural Language Processing: A Review](https://mlsanity.com/paper/2110.10470/) (2021)
- [In-Context Demonstration Selection with Cross Entropy Difference](https://mlsanity.com/paper/2305.14726/) (2023)
- [Text Compression-aided Transformer Encoding](https://mlsanity.com/paper/2102.05951/) (2021)
- [Enhanced Speaker-aware Multi-party Multi-turn Dialogue Comprehension](https://mlsanity.com/paper/2109.04066/) (2021)
- [Seeking Common but Distinguishing Difference, A Joint Aspect-based Sentiment Analysis Model](https://mlsanity.com/paper/2111.09634/) (2021)
- [You Need to Read Again: Multi-granularity Perception Network for Moment Retrieval in Videos](https://mlsanity.com/paper/2205.12886/) (2022)
- [Detecting (Un)answerability in Large Language Models with Linear Directions](https://mlsanity.com/paper/2509.22449/) (2025)
- [Advances in Multi-turn Dialogue Comprehension: A Survey](https://mlsanity.com/paper/2103.03125/) (2021)
- [How to Query Language Models?](https://mlsanity.com/paper/2108.01928/) (2021)
- [Evaluating ChatGPT as a Question Answering System: A Comprehensive Analysis and Comparison with Existing Models](https://mlsanity.com/paper/2312.07592/) (2023)
- [Multi-turn Dialogue Reading Comprehension with Pivot Turns and Knowledge](https://mlsanity.com/paper/2102.05474/) (2021)
- [Improved and Efficient Conversational Slot Labeling through Question Answering](https://mlsanity.com/paper/2204.02123/) (2022)
- [Dialogue-oriented Pre-training](https://mlsanity.com/paper/2106.00420/) (2021)
- [Can Question Rewriting Help Conversational Question Answering?](https://mlsanity.com/paper/2204.06239/) (2022)
- [Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning](https://mlsanity.com/paper/2205.00731/) (2022)
- [Evaluating Pre-Trained Models for User Feedback Analysis in Software Engineering: A Study on Classification of App-Reviews](https://mlsanity.com/paper/2104.05861/) (2021)
- [VLSP 2021 - ViMRC Challenge: Vietnamese Machine Reading Comprehension](https://mlsanity.com/paper/2203.11400/) (2022)

## Abstract (arXiv)

Machine reading comprehension (MRC) is an AI challenge that requires machine to determine the correct answers to questions based on a given passage. MRC systems must not only answer question when necessary but also distinguish when no answer is available according to the given passage and then tactfully abstain from answering. When unanswerable questions are involved in the MRC task, an essential verification module called verifier is especially required in addition to the encoder, though the latest practice on MRC modeling still most benefits from adopting well pre-trained language models as the encoder block by only focusing on the "reading". This paper devotes itself to exploring better verifier design for the MRC task with unanswerable questions. Inspired by how humans solve reading comprehension questions, we proposed a retrospective reader (Retro-Reader) that integrates two stages of reading and verification strategies: 1) sketchy reading that briefly investigates the overall interactions of passage and question, and yield an initial judgment; 2) intensive reading that verifies the answer and gives the final prediction. The proposed reader is evaluated on two benchmark MRC challenge datasets SQuAD2.0 and NewsQA, achieving new state-of-the-art results. Significance tests show that our model is significantly better than the strong ELECTRA and ALBERT baselines. A series of analysis is also conducted to interpret the effectiveness of the proposed reader.