# Dynamic Coattention Networks For Question Answering

arXiv: https://arxiv.org/abs/1611.01604 · HTML: https://mlsanity.com/paper/1611.01604/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2016.

## Built on by (most cited first, 30 of 49)

- [OpenCQA: Open-ended Question Answering with Charts](https://mlsanity.com/paper/2210.06628/) (2022)
- [Natural Language Video Localization: A Revisit in Span-based Question Answering Framework](https://mlsanity.com/paper/2102.13558/) (2021)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Biomedical Question Answering: A Survey of Approaches and Challenges](https://mlsanity.com/paper/2102.05281/) (2021)
- [Paradigm Shift in Natural Language Processing](https://mlsanity.com/paper/2109.12575/) (2021)
- [SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising](https://mlsanity.com/paper/2105.07911/) (2021)
- [Pushing the Limits of ChatGPT on NLP Tasks](https://mlsanity.com/paper/2306.09719/) (2023)
- [Introspective Distillation for Robust Question Answering](https://mlsanity.com/paper/2111.01026/) (2021)
- [Video Activity Localisation with Uncertainties in Temporal Boundary](https://mlsanity.com/paper/2206.12923/) (2022)
- [Spatio-Temporal Self-Attention Network for Video Saliency Prediction](https://mlsanity.com/paper/2108.10696/) (2021)
- [A Survey on Video Moment Localization](https://mlsanity.com/paper/2306.07515/) (2023)
- [Affect2MM: Affective Analysis of Multimedia Content Using Emotion Causality](https://mlsanity.com/paper/2103.06541/) (2021)
- [Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices](https://mlsanity.com/paper/2112.03572/) (2021)
- [When Search Meets Recommendation: Learning Disentangled Search Representation for Recommendation](https://mlsanity.com/paper/2305.10822/) (2023)
- [From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering](https://mlsanity.com/paper/2205.11729/) (2022)
- [Multitask Pre-training of Modular Prompt for Chinese Few-Shot Learning](https://mlsanity.com/paper/2210.07565/) (2022)
- [Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2204.02791/) (2022)
- [Neural Attention Models in Deep Learning: Survey and Taxonomy](https://mlsanity.com/paper/2112.05909/) (2021)
- [On the Usability of Transformers-based models for a French Question-Answering task](https://mlsanity.com/paper/2207.09150/) (2022)
- [LAIT: Efficient Multi-Segment Encoding in Transformers with Layer-Adjustable Interaction](https://mlsanity.com/paper/2305.19585/) (2023)
- [Learning to Rehearse in Long Sequence Memorization](https://mlsanity.com/paper/2106.01096/) (2021)
- [Enhance Long Text Understanding via Distilled Gist Detector from Abstractive Summarization](https://mlsanity.com/paper/2110.04741/) (2021)
- [Localizing Events in Videos with Multimodal Queries](https://mlsanity.com/paper/2406.10079/) (2024)
- [Coarse-grained decomposition and fine-grained interaction for multi-hop question answering](https://mlsanity.com/paper/2101.05988/) (2021)
- [MINIMAL: Mining Models for Data Free Universal Adversarial Triggers](https://mlsanity.com/paper/2109.12406/) (2021)
- [Adapting Pre-trained Generative Models for Extractive Question Answering](https://mlsanity.com/paper/2311.02961/) (2023)
- [A Coarse to Fine Question Answering System based on Reinforcement Learning](https://mlsanity.com/paper/2106.00257/) (2021)
- [CAR-Net: Unsupervised Co-Attention Guided Registration Network for Joint Registration and Structure Learning](https://mlsanity.com/paper/2106.06637/) (2021)
- [Clozer: Adaptable Data Augmentation for Cloze-style Reading Comprehension](https://mlsanity.com/paper/2203.16027/) (2022)
- [Unified BERT for Few-shot Natural Language Understanding](https://mlsanity.com/paper/2206.12094/) (2022)

## Abstract (arXiv)

Several deep learning models have been proposed for question answering. However, due to their single-pass nature, they have no way to recover from local maxima corresponding to incorrect answers. To address this problem, we introduce the Dynamic Coattention Network (DCN) for question answering. The DCN first fuses co-dependent representations of the question and the document in order to focus on relevant parts of both. Then a dynamic pointing decoder iterates over potential answer spans. This iterative procedure enables the model to recover from initial local maxima corresponding to incorrect answers. On the Stanford question answering dataset, a single DCN model improves the previous state of the art from 71.0% F1 to 75.9%, while a DCN ensemble obtains 80.4% F1.