Multi-span Style Extraction for Generative Reading Comprehension

09/15/2020
by   Junjie Yang, et al.
0

Generative machine reading comprehension (MRC) requires a model to generate well-formed answers. For this type of MRC, answer generation method is crucial to the model performance. However, generative models, which are supposed to be the right model for the task, in generally perform poorly. At the same time, single-span extraction models have been proven effective for extractive MRC, where the answer is constrained to a single span in the passage. Nevertheless, they generally suffer from generating incomplete answers or introducing redundant words when applied to the generative MRC. Thus, we extend the single-span extraction method to multi-span, proposing a new framework which enables generative MRC to be smoothly solved as multi-span extraction. Thorough experiments demonstrate that this novel approach can alleviate the dilemma between generative models and single-span models and produce answers with better-formed syntax and semantics. We will open-source our code for the research community.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/14/2020

Composing Answer from Multi-spans for Reading Comprehension

This paper presents a novel method to generate answers for non-extractio...
research
01/08/2019

Multi-style Generative Reading Comprehension

This study focuses on the task of multi-passage reading comprehension (R...
research
08/15/2019

A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning

Rapid progress has been made in the field of reading comprehension and q...
research
09/29/2020

MaP: A Matrix-based Prediction Approach to Improve Span Extraction in Machine Reading Comprehension

Span extraction is an essential problem in machine reading comprehension...
research
09/25/2020

No Answer is Better Than Wrong Answer: A Reflection Model for Document Level Machine Reading Comprehension

The Natural Questions (NQ) benchmark set brings new challenges to Machin...
research
12/05/2018

Weighted Global Normalization for Multiple Choice ReadingComprehension over Long Documents

Motivated by recent evidence pointing out the fragility of high-performi...
research
03/30/2022

Clozer: Adaptable Data Augmentation for Cloze-style Reading Comprehension

Task-adaptive pre-training (TAPT) alleviates the lack of labelled data a...

Please sign up or login with your details

Forgot password? Click here to reset