Multi-style Generative Reading Comprehension

01/08/2019
by   Kyosuke Nishida, et al.
0

This study focuses on the task of multi-passage reading comprehension (RC) where an answer is provided in natural language. Current mainstream approaches treat RC by extracting the answer span from the provided passages and cannot generate an abstractive summary from the given question and passages. Moreover, they cannot utilize and control different styles of answers, such as concise phrases and well-formed sentences, within a model. In this study, we propose a style-controllable Multi-source Abstractive Summarization model for QUEstion answering, called Masque. The model is an end-to-end deep neural network that can generate answers conditioned on a given style. Experiments with MS MARCO 2.1 show that our model achieved state-of-the-art performance on two tasks with different answer styles.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/05/2022

Multi Document Reading Comprehension

Reading Comprehension (RC) is a task of answering a question from a give...
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
09/15/2020

Multi-span Style Extraction for Generative Reading Comprehension

Generative machine reading comprehension (MRC) requires a model to gener...
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...
research
09/19/2019

What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering

Multi-hop textual question answering requires combining information from...
research
08/31/2018

Retrieve-and-Read: Multi-task Learning of Information Retrieval and Reading Comprehension

This study considers the task of machine reading at scale (MRS) wherein,...
research
09/14/2021

Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension

How can we generate concise explanations for multi-hop Reading Comprehen...

Please sign up or login with your details

Forgot password? Click here to reset