Follow-Up question generation using neural tensor network-based domain ontology population in an interview coaching system

研究成果: Conference article

摘要

This study proposes an approach to follow-up question generation based on a populated domain ontology in a conversational interview coaching system. The purpose of this study is to generate the follow-up questions which are more related to the meaning beyond the literal content in the user's answer based on the background knowledge in a populated domain ontology. Firstly, a convolutional neural tensor network (CNTN) was applied for selecting a key sentence from the user answer. Secondly, the neural tensor network (NTN) was used to model the relationship between the subjects and objects in the resource description framework (RDF) triple, defined as (subject, predicate, object), in each predicate from the ConceptNet for domain ontology population. The words in the key sentence were then used to retrieve relevant triples from the domain ontology for filling into the slots in the question templates to generate potential follow-up questions. Finally, the CNTN-based sentence matching model was employed to choose the one most related to the answer sentence as the final follow-up question. This study used 5-fold cross-validation for performance evaluation. The experimental results showed the generation performance in the proposed model was higher than the traditional method. The performance of key sentence selection model achieved 81.94%, and the sentence matching model achieved 92.28%.

指紋

Domain Ontology
Tensors
Ontology
Tensor
Model Matching
Predicate
Selection Model
Cross-validation
Performance Evaluation
Template
Fold
Choose
Resources
Neural Networks
Coaching
Experimental Results
Model
Object

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

引用此文

@article{e3456d1ef75946a4aa217d9a4aa751f3,
title = "Follow-Up question generation using neural tensor network-based domain ontology population in an interview coaching system",
abstract = "This study proposes an approach to follow-up question generation based on a populated domain ontology in a conversational interview coaching system. The purpose of this study is to generate the follow-up questions which are more related to the meaning beyond the literal content in the user's answer based on the background knowledge in a populated domain ontology. Firstly, a convolutional neural tensor network (CNTN) was applied for selecting a key sentence from the user answer. Secondly, the neural tensor network (NTN) was used to model the relationship between the subjects and objects in the resource description framework (RDF) triple, defined as (subject, predicate, object), in each predicate from the ConceptNet for domain ontology population. The words in the key sentence were then used to retrieve relevant triples from the domain ontology for filling into the slots in the question templates to generate potential follow-up questions. Finally, the CNTN-based sentence matching model was employed to choose the one most related to the answer sentence as the final follow-up question. This study used 5-fold cross-validation for performance evaluation. The experimental results showed the generation performance in the proposed model was higher than the traditional method. The performance of key sentence selection model achieved 81.94{\%}, and the sentence matching model achieved 92.28{\%}.",
author = "Su, {Ming Hsiang} and Wu, {Chung Hsien} and Yi Chang",
year = "2019",
month = "1",
day = "1",
doi = "10.21437/Interspeech.2019-1300",
language = "English",
volume = "2019-September",
pages = "4185--4189",
journal = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
issn = "2308-457X",

}

TY - JOUR

T1 - Follow-Up question generation using neural tensor network-based domain ontology population in an interview coaching system

AU - Su, Ming Hsiang

AU - Wu, Chung Hsien

AU - Chang, Yi

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This study proposes an approach to follow-up question generation based on a populated domain ontology in a conversational interview coaching system. The purpose of this study is to generate the follow-up questions which are more related to the meaning beyond the literal content in the user's answer based on the background knowledge in a populated domain ontology. Firstly, a convolutional neural tensor network (CNTN) was applied for selecting a key sentence from the user answer. Secondly, the neural tensor network (NTN) was used to model the relationship between the subjects and objects in the resource description framework (RDF) triple, defined as (subject, predicate, object), in each predicate from the ConceptNet for domain ontology population. The words in the key sentence were then used to retrieve relevant triples from the domain ontology for filling into the slots in the question templates to generate potential follow-up questions. Finally, the CNTN-based sentence matching model was employed to choose the one most related to the answer sentence as the final follow-up question. This study used 5-fold cross-validation for performance evaluation. The experimental results showed the generation performance in the proposed model was higher than the traditional method. The performance of key sentence selection model achieved 81.94%, and the sentence matching model achieved 92.28%.

AB - This study proposes an approach to follow-up question generation based on a populated domain ontology in a conversational interview coaching system. The purpose of this study is to generate the follow-up questions which are more related to the meaning beyond the literal content in the user's answer based on the background knowledge in a populated domain ontology. Firstly, a convolutional neural tensor network (CNTN) was applied for selecting a key sentence from the user answer. Secondly, the neural tensor network (NTN) was used to model the relationship between the subjects and objects in the resource description framework (RDF) triple, defined as (subject, predicate, object), in each predicate from the ConceptNet for domain ontology population. The words in the key sentence were then used to retrieve relevant triples from the domain ontology for filling into the slots in the question templates to generate potential follow-up questions. Finally, the CNTN-based sentence matching model was employed to choose the one most related to the answer sentence as the final follow-up question. This study used 5-fold cross-validation for performance evaluation. The experimental results showed the generation performance in the proposed model was higher than the traditional method. The performance of key sentence selection model achieved 81.94%, and the sentence matching model achieved 92.28%.

UR - http://www.scopus.com/inward/record.url?scp=85074727097&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074727097&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2019-1300

DO - 10.21437/Interspeech.2019-1300

M3 - Conference article

AN - SCOPUS:85074727097

VL - 2019-September

SP - 4185

EP - 4189

JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

SN - 2308-457X

ER -