Multitask learning for multilingual intent detection and slot filling in dialogue systems
Dialogue systems are becoming an ubiquitous presence in our everyday lives having a huge impact on business and society. Spoken language understanding (SLU) is the critical component of every goal-oriented dialogue system or any conversational system. The understanding of the user utterance is cruci...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/170548 |
| _version_ | 1811679279635759104 |
|---|---|
| author | Firdaus, Mauajama Ekbal, Asif Cambria, Erik |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Firdaus, Mauajama Ekbal, Asif Cambria, Erik |
| author_sort | Firdaus, Mauajama |
| collection | NTU |
| description | Dialogue systems are becoming an ubiquitous presence in our everyday lives having a huge impact on business and society. Spoken language understanding (SLU) is the critical component of every goal-oriented dialogue system or any conversational system. The understanding of the user utterance is crucial for assisting the user in achieving their desired objectives. Future-generation systems need to be able to handle the multilinguality issue. Hence, the development of conversational agents becomes challenging as it needs to understand the different languages along with the semantic meaning of the given utterance. In this work, we propose a multilingual multitask approach to fuse the two primary SLU tasks, namely, intent detection and slot filling for three different languages. While intent detection deals with identifying user's goal or purpose, slot filling captures the appropriate user utterance information in the form of slots. As both of these tasks are highly correlated, we propose a multitask strategy to tackle these two tasks concurrently. We employ a transformer as a shared sentence encoder for the three languages, i.e., English, Hindi, and Bengali. Experimental results show that the proposed model achieves an improvement for all the languages for both the tasks of SLU. The multi-lingual multi-task (MLMT) framework shows an improvement of more than 2% in case of intent accuracy and 3% for slot F1 score in comparison to the single task models. Also, there is an increase of more than 1 point intent accuracy and 2 points slot F1 score in the MLMT model as opposed to the language specific frameworks. |
| first_indexed | 2024-10-01T03:06:38Z |
| format | Journal Article |
| id | ntu-10356/170548 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:06:38Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1705482023-09-19T02:46:56Z Multitask learning for multilingual intent detection and slot filling in dialogue systems Firdaus, Mauajama Ekbal, Asif Cambria, Erik School of Computer Science and Engineering Engineering::Computer science and engineering Multitask Learning Multilingual Analysis Dialogue systems are becoming an ubiquitous presence in our everyday lives having a huge impact on business and society. Spoken language understanding (SLU) is the critical component of every goal-oriented dialogue system or any conversational system. The understanding of the user utterance is crucial for assisting the user in achieving their desired objectives. Future-generation systems need to be able to handle the multilinguality issue. Hence, the development of conversational agents becomes challenging as it needs to understand the different languages along with the semantic meaning of the given utterance. In this work, we propose a multilingual multitask approach to fuse the two primary SLU tasks, namely, intent detection and slot filling for three different languages. While intent detection deals with identifying user's goal or purpose, slot filling captures the appropriate user utterance information in the form of slots. As both of these tasks are highly correlated, we propose a multitask strategy to tackle these two tasks concurrently. We employ a transformer as a shared sentence encoder for the three languages, i.e., English, Hindi, and Bengali. Experimental results show that the proposed model achieves an improvement for all the languages for both the tasks of SLU. The multi-lingual multi-task (MLMT) framework shows an improvement of more than 2% in case of intent accuracy and 3% for slot F1 score in comparison to the single task models. Also, there is an increase of more than 1 point intent accuracy and 2 points slot F1 score in the MLMT model as opposed to the language specific frameworks. Agency for Science, Technology and Research (A*STAR) This research is supported by the Imprint 2C sponsored project titled ‘‘Sevak-An Intelligent Indian Language Chatbot’’. This research is also supported by the Agency for Science, Technology and Research (A*STAR) under its AME Programmatic Funding Scheme (Project #A18A2b0046). 2023-09-19T02:46:56Z 2023-09-19T02:46:56Z 2023 Journal Article Firdaus, M., Ekbal, A. & Cambria, E. (2023). Multitask learning for multilingual intent detection and slot filling in dialogue systems. Information Fusion, 91, 299-315. https://dx.doi.org/10.1016/j.inffus.2022.09.029 1566-2535 https://hdl.handle.net/10356/170548 10.1016/j.inffus.2022.09.029 2-s2.0-85140879679 91 299 315 en A18A2b0046 Information Fusion © 2022 Elsevier B.V. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Multitask Learning Multilingual Analysis Firdaus, Mauajama Ekbal, Asif Cambria, Erik Multitask learning for multilingual intent detection and slot filling in dialogue systems |
| title | Multitask learning for multilingual intent detection and slot filling in dialogue systems |
| title_full | Multitask learning for multilingual intent detection and slot filling in dialogue systems |
| title_fullStr | Multitask learning for multilingual intent detection and slot filling in dialogue systems |
| title_full_unstemmed | Multitask learning for multilingual intent detection and slot filling in dialogue systems |
| title_short | Multitask learning for multilingual intent detection and slot filling in dialogue systems |
| title_sort | multitask learning for multilingual intent detection and slot filling in dialogue systems |
| topic | Engineering::Computer science and engineering Multitask Learning Multilingual Analysis |
| url | https://hdl.handle.net/10356/170548 |
| work_keys_str_mv | AT firdausmauajama multitasklearningformultilingualintentdetectionandslotfillingindialoguesystems AT ekbalasif multitasklearningformultilingualintentdetectionandslotfillingindialoguesystems AT cambriaerik multitasklearningformultilingualintentdetectionandslotfillingindialoguesystems |