Dynamic Coattention Networks For Question Answering

by   Caiming Xiong, et al.

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 80.4


Question Dependent Recurrent Entity Network for Question Answering

Question Answering is a task which requires building models capable of p...

RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question Answering

Open-Domain Question Answering (ODQA) systems necessitate a reader model...

Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering

We address the problem of extractive question answering using document-l...

Is Sluice Resolution really just Question Answering?

Sluice resolution is a problem where a system needs to output the corres...

UIT-ViCoV19QA: A Dataset for COVID-19 Community-based Question Answering on Vietnamese Language

For the last two years, from 2020 to 2021, COVID-19 has broken disease p...

DCN+: Mixed Objective and Deep Residual Coattention for Question Answering

Traditional models for question answering optimize using cross entropy l...

Overinformative Question Answering by Humans and Machines

When faced with a polar question, speakers often provide overinformative...

Code Repositories


Dynamic Coattention Network Plus (DCN+) TensorFlow implementation. Question answering using Deep NLP.

view repo


Implementation of Dynamic Coattention Network for Question Answering

view repo


Attempt to reproduce results of Dynamic Coattention Network (DCN)

view repo

Please sign up or login with your details

Forgot password? Click here to reset