Thai Paraphrasing Tool for Chatbot Intent Recognition Training

This paper introduced a novel tool to automatically generate Thai paraphrased sentences specialized for intent recognition training. This technique is devised to improve intent recognition accuracy and reduce the training time, especially during the creation of applications like Thai natural languag...

Full description

Saved in:
Bibliographic Details
Main Author: Sirikasem D.
Other Authors: Mahidol University
Format: Conference or Workshop Item
Published: 2023
Subjects:
Online Access:https://repository.li.mahidol.ac.th/handle/123456789/84304
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Mahidol University
id th-mahidol.84304
record_format dspace
spelling th-mahidol.843042023-06-19T00:02:26Z Thai Paraphrasing Tool for Chatbot Intent Recognition Training Sirikasem D. Mahidol University Computer Science This paper introduced a novel tool to automatically generate Thai paraphrased sentences specialized for intent recognition training. This technique is devised to improve intent recognition accuracy and reduce the training time, especially during the creation of applications like Thai natural language-based games and chatbots. The switching if-conjunction clauses in question sentences and the thesaurus-based paraphrasing methods have been explored. For the evaluation, a group of participants used the prototype tool to develop Thai chatbots. Which were tested to recognize question-type messages in the Thai national identification card domain provided by another group. The results demonstrated that the proposed techniques increase the accuracy F1 score compared to the state-ofthe-art pattern-aided chatbot by approximately 39%. On average, expert chatbot developers scored 8.25 out of 10 points on the prototype tool satisfaction. 2023-06-18T17:02:26Z 2023-06-18T17:02:26Z 2022-01-01 Conference Paper ICSEC 2022 - International Computer Science and Engineering Conference 2022 (2022) , 111-116 10.1109/ICSEC56337.2022.10049337 2-s2.0-85149678753 https://repository.li.mahidol.ac.th/handle/123456789/84304 SCOPUS
institution Mahidol University
building Mahidol University Library
continent Asia
country Thailand
Thailand
content_provider Mahidol University Library
collection Mahidol University Institutional Repository
topic Computer Science
spellingShingle Computer Science
Sirikasem D.
Thai Paraphrasing Tool for Chatbot Intent Recognition Training
description This paper introduced a novel tool to automatically generate Thai paraphrased sentences specialized for intent recognition training. This technique is devised to improve intent recognition accuracy and reduce the training time, especially during the creation of applications like Thai natural language-based games and chatbots. The switching if-conjunction clauses in question sentences and the thesaurus-based paraphrasing methods have been explored. For the evaluation, a group of participants used the prototype tool to develop Thai chatbots. Which were tested to recognize question-type messages in the Thai national identification card domain provided by another group. The results demonstrated that the proposed techniques increase the accuracy F1 score compared to the state-ofthe-art pattern-aided chatbot by approximately 39%. On average, expert chatbot developers scored 8.25 out of 10 points on the prototype tool satisfaction.
author2 Mahidol University
author_facet Mahidol University
Sirikasem D.
format Conference or Workshop Item
author Sirikasem D.
author_sort Sirikasem D.
title Thai Paraphrasing Tool for Chatbot Intent Recognition Training
title_short Thai Paraphrasing Tool for Chatbot Intent Recognition Training
title_full Thai Paraphrasing Tool for Chatbot Intent Recognition Training
title_fullStr Thai Paraphrasing Tool for Chatbot Intent Recognition Training
title_full_unstemmed Thai Paraphrasing Tool for Chatbot Intent Recognition Training
title_sort thai paraphrasing tool for chatbot intent recognition training
publishDate 2023
url https://repository.li.mahidol.ac.th/handle/123456789/84304
_version_ 1781413759232770048