# Stochastic Answer Networks for Machine Reading Comprehension

arXiv: https://arxiv.org/abs/1712.03556 · HTML: https://mlsanity.com/paper/1712.03556/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2017.

## Built on by (most cited first, 22 of 22)

- [ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation](https://mlsanity.com/paper/2101.08382/) (2021)
- [NoiseQA: Challenge Set Evaluation for User-Centric Question Answering](https://mlsanity.com/paper/2102.08345/) (2021)
- [Do Question Answering Modeling Improvements Hold Across Benchmarks?](https://mlsanity.com/paper/2102.01065/) (2021)
- [Is Everything in Order? A Simple Way to Order Sentences](https://mlsanity.com/paper/2104.07064/) (2021)
- [JaQuAD: Japanese Question Answering Dataset for Machine Reading Comprehension](https://mlsanity.com/paper/2202.01764/) (2022)
- [iSEA: An Interactive Pipeline for Semantic Error Analysis of NLP Models](https://mlsanity.com/paper/2203.04408/) (2022)
- [GenSco: Can Question Decomposition based Passage Alignment improve Question Answering?](https://mlsanity.com/paper/2407.10245/) (2024)
- [MCR-Net: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension](https://mlsanity.com/paper/2103.04567/) (2021)
- [A Comprehensive Empirical Evaluation of Existing Word Embedding Approaches](https://mlsanity.com/paper/2303.07196/) (2023)
- [Engineering A Large Language Model From Scratch](https://mlsanity.com/paper/2401.16736/) (2024)
- [Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey](https://mlsanity.com/paper/2411.09166/) (2024)
- [Evaluating List Construction and Temporal Understanding capabilities of Large Language Models](https://mlsanity.com/paper/2506.21783/) (2025)
- [Understanding in Artificial Intelligence](https://mlsanity.com/paper/2101.06573/) (2021)
- [Automatic Task Requirements Writing Evaluation via Machine Reading Comprehension](https://mlsanity.com/paper/2107.07957/) (2021)
- [An Automated Question-Answering Framework Based on Evolution Algorithm](https://mlsanity.com/paper/2201.10797/) (2022)
- [Pruned Graph Neural Network for Short Story Ordering](https://mlsanity.com/paper/2203.06778/) (2022)
- [Deep Understanding based Multi-Document Machine Reading Comprehension](https://mlsanity.com/paper/2204.03494/) (2022)
- [Good Intentions: Adaptive Parameter Management via Intent Signaling](https://mlsanity.com/paper/2206.00470/) (2022)
- [An Understanding-Oriented Robust Machine Reading Comprehension Model](https://mlsanity.com/paper/2207.00187/) (2022)
- [Feature-augmented Machine Reading Comprehension with Auxiliary Tasks](https://mlsanity.com/paper/2211.09438/) (2022)
- [PEvoLM: Protein Sequence Evolutionary Information Language Model](https://mlsanity.com/paper/2308.08578/) (2023)
- [Perturbation-based Active Learning for Question Answering](https://mlsanity.com/paper/2311.02345/) (2023)

## Abstract (arXiv)

We propose a simple yet robust stochastic answer network (SAN) that simulates multi-step reasoning in machine reading comprehension. Compared to previous work such as ReasoNet which used reinforcement learning to determine the number of steps, the unique feature is the use of a kind of stochastic prediction dropout on the answer module (final layer) of the neural network during the training. We show that this simple trick improves robustness and achieves results competitive to the state-of-the-art on the Stanford Question Answering Dataset (SQuAD), the Adversarial SQuAD, and the Microsoft MAchine Reading COmprehension Dataset (MS MARCO).