Question Difficulty Estimation Based on Attention Model for Question Answering

This paper addresses a question difficulty estimation of which goal is to estimate the difficulty level of a given question in question-answering (QA) tasks. Since a question in the tasks is composed of a questionary sentence and a set of information components such as a description and candidate an...

Full description

Bibliographic Details
Main Authors: Hyun-Je Song, Su-Hwan Yoon, Seong-Bae Park
Format: Article
Language:English
Published: MDPI AG 2021-12-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/11/24/12023
_version_ 1827674203937046528
author Hyun-Je Song
Su-Hwan Yoon
Seong-Bae Park
author_facet Hyun-Je Song
Su-Hwan Yoon
Seong-Bae Park
author_sort Hyun-Je Song
collection DOAJ
description This paper addresses a question difficulty estimation of which goal is to estimate the difficulty level of a given question in question-answering (QA) tasks. Since a question in the tasks is composed of a questionary sentence and a set of information components such as a description and candidate answers, it is important to model the relationship among the information components to estimate the difficulty level of the question. However, existing approaches to this task modeled a simple relationship such as a relationship between a questionary sentence and a description, but such simple relationships are insufficient to predict the difficulty level accurately. Therefore, this paper proposes an attention-based model to consider the complicated relationship among the information components. The proposed model first represents bi-directional relationships between a questionary sentence and each information component using a dual multi-head co-attention, since the questionary sentence is a key factor in the QA questions and it affects and is affected by information components. Then, the proposed model considers inter-information relationship over the bi-directional representations through a self-attention model. The inter-information relationship helps predict the difficulty of the questions accurately which require reasoning over multiple kinds of information components. The experimental results from three well-known and real-world QA data sets prove that the proposed model outperforms the previous state-of-the-art and pre-trained language model baselines. It is also shown that the proposed model is robust against the increase of the number of information components.
first_indexed 2024-03-10T04:36:18Z
format Article
id doaj.art-0635d9a3cd634d829dbc18b175114668
institution Directory Open Access Journal
issn 2076-3417
language English
last_indexed 2024-03-10T04:36:18Z
publishDate 2021-12-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj.art-0635d9a3cd634d829dbc18b1751146682023-11-23T03:41:59ZengMDPI AGApplied Sciences2076-34172021-12-0111241202310.3390/app112412023Question Difficulty Estimation Based on Attention Model for Question AnsweringHyun-Je Song0Su-Hwan Yoon1Seong-Bae Park2Department of Information Technology, Jeonbuk National University, Jeonju 54896, KoreaDepartment of Computer Science and Engineering, Kyung Hee University, Youngin 17104, KoreaDepartment of Computer Science and Engineering, Kyung Hee University, Youngin 17104, KoreaThis paper addresses a question difficulty estimation of which goal is to estimate the difficulty level of a given question in question-answering (QA) tasks. Since a question in the tasks is composed of a questionary sentence and a set of information components such as a description and candidate answers, it is important to model the relationship among the information components to estimate the difficulty level of the question. However, existing approaches to this task modeled a simple relationship such as a relationship between a questionary sentence and a description, but such simple relationships are insufficient to predict the difficulty level accurately. Therefore, this paper proposes an attention-based model to consider the complicated relationship among the information components. The proposed model first represents bi-directional relationships between a questionary sentence and each information component using a dual multi-head co-attention, since the questionary sentence is a key factor in the QA questions and it affects and is affected by information components. Then, the proposed model considers inter-information relationship over the bi-directional representations through a self-attention model. The inter-information relationship helps predict the difficulty of the questions accurately which require reasoning over multiple kinds of information components. The experimental results from three well-known and real-world QA data sets prove that the proposed model outperforms the previous state-of-the-art and pre-trained language model baselines. It is also shown that the proposed model is robust against the increase of the number of information components.https://www.mdpi.com/2076-3417/11/24/12023attention modeldual multi-head attentioninter-information relationshipquestion answeringquestion difficult estimation
spellingShingle Hyun-Je Song
Su-Hwan Yoon
Seong-Bae Park
Question Difficulty Estimation Based on Attention Model for Question Answering
Applied Sciences
attention model
dual multi-head attention
inter-information relationship
question answering
question difficult estimation
title Question Difficulty Estimation Based on Attention Model for Question Answering
title_full Question Difficulty Estimation Based on Attention Model for Question Answering
title_fullStr Question Difficulty Estimation Based on Attention Model for Question Answering
title_full_unstemmed Question Difficulty Estimation Based on Attention Model for Question Answering
title_short Question Difficulty Estimation Based on Attention Model for Question Answering
title_sort question difficulty estimation based on attention model for question answering
topic attention model
dual multi-head attention
inter-information relationship
question answering
question difficult estimation
url https://www.mdpi.com/2076-3417/11/24/12023
work_keys_str_mv AT hyunjesong questiondifficultyestimationbasedonattentionmodelforquestionanswering
AT suhwanyoon questiondifficultyestimationbasedonattentionmodelforquestionanswering
AT seongbaepark questiondifficultyestimationbasedonattentionmodelforquestionanswering