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

10/31/2017
by   Caiming Xiong, et al.
0

Traditional models for question answering optimize using cross entropy loss, which encourages exact answers at the cost of penalizing nearby or overlapping answers that are sometimes equally accurate. We propose a mixed objective that combines cross entropy loss with self-critical policy learning. The objective uses rewards derived from word overlap to solve the misalignment between evaluation metric and optimization objective. In addition to the mixed objective, we improve dynamic coattention networks (DCN) with a deep residual coattention encoder that is inspired by recent work in deep self-attention and residual networks. Our proposals improve model performance across question types and input lengths, especially for long questions that requires the ability to capture long-term dependencies. On the Stanford Question Answering Dataset, our model achieves state-of-the-art results with 75.1 accuracy and 83.1 and 86.0

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/02/2017

A Simple Loss Function for Improving the Convergence and Accuracy of Visual Question Answering Models

Visual question answering as recently proposed multimodal learning task ...
research
05/31/2023

Attention-Based Methods For Audio Question Answering

Audio question answering (AQA) is the task of producing natural language...
research
11/05/2016

Dynamic Coattention Networks For Question Answering

Several deep learning models have been proposed for question answering. ...
research
05/04/2017

Machine Comprehension by Text-to-Text Neural Question Generation

We propose a recurrent neural model that generates natural-language ques...
research
05/14/2018

Did the Model Understand the Question?

We analyze state-of-the-art deep learning models for three tasks: questi...
research
09/08/2021

Cross-Policy Compliance Detection via Question Answering

Policy compliance detection is the task of ensuring that a scenario conf...
research
05/08/2017

Reinforced Mnemonic Reader for Machine Comprehension

In this paper, we introduce the Reinforced Mnemonic Reader for machine c...

Please sign up or login with your details

Forgot password? Click here to reset