Unsupervised Explanation Generation for Machine Reading Comprehension

11/13/2020
by   Yiming Cui, et al.
0

With the blooming of various Pre-trained Language Models (PLMs), Machine Reading Comprehension (MRC) has embraced significant improvements on various benchmarks and even surpass human performances. However, the existing works only target on the accuracy of the final predictions and neglect the importance of the explanations for the prediction, which is a big obstacle when utilizing these models in real-life applications to convince humans. In this paper, we propose a self-explainable framework for the machine reading comprehension task. The main idea is that the proposed system tries to use less passage information and achieve similar results compared to the system that uses the whole passage, while the filtered passage will be used as explanations. We carried out experiments on three multiple-choice MRC datasets, and found that the proposed system could achieve consistent improvements over baseline systems. To evaluate the explainability, we compared our approach with the traditional attention mechanism in human evaluations and found that the proposed system has a notable advantage over the latter one.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/10/2021

ExpMRC: Explainability Evaluation for Machine Reading Comprehension

Achieving human-level performance on some of Machine Reading Comprehensi...
research
08/26/2021

Understanding Attention in Machine Reading Comprehension

Achieving human-level performance on some of Machine Reading Comprehensi...
research
04/09/2021

Evaluating Explanations for Reading Comprehension with Realistic Counterfactuals

Token-level attributions have been extensively studied to explain model ...
research
10/24/2020

Improved Synthetic Training for Reading Comprehension

Automatically generated synthetic training examples have been shown to i...
research
04/04/2020

Prerequisites for Explainable Machine Reading Comprehension: A Position Paper

Machine reading comprehension (MRC) has received considerable attention ...
research
09/28/2019

Integrated Triaging for Fast Reading Comprehension

Although according to several benchmarks automatic machine reading compr...
research
09/11/2021

Extract, Integrate, Compete: Towards Verification Style Reading Comprehension

In this paper, we present a new verification style reading comprehension...

Please sign up or login with your details

Forgot password? Click here to reset