TY - GEN
T1 - Thai Paraphrasing Tool for Chatbot Intent Recognition Training
AU - Sirikasem, Darlyn
AU - Pongpaichet, Siripen
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - Thai language processing
KW - chatbot
KW - intent recognition
KW - paraphrase generation
KW - text augment
UR - https://www.scopus.com/pages/publications/85149678753
U2 - 10.1109/ICSEC56337.2022.10049337
DO - 10.1109/ICSEC56337.2022.10049337
M3 - Conference contribution
AN - SCOPUS:85149678753
T3 - ICSEC 2022 - International Computer Science and Engineering Conference 2022
SP - 111
EP - 116
BT - ICSEC 2022 - International Computer Science and Engineering Conference 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 26th International Computer Science and Engineering Conference, ICSEC 2022
Y2 - 21 December 2022 through 23 December 2022
ER -