What is it about?
Any NLU systems such as a chatbot needs to be regularly maintained and updated as time passes and new user behaviour emerges. While this has been widely studied, there is a lack of coverage or testing on multilingual data, hindering the application to larger international businesses. Our work leverages recent large language models to address this problem.
Featured Image
Photo by Igor Omilaev on Unsplash
Why is it important?
Our proposed method leverages the latest advances in LLM to achieve state-of-the-art performances. Practically, our system is able to help businesses capture changes in user behaviour, allowing better allocation of resources. It also requires far less human effort than existing approaches to multilingual intent discovery.
Read the Original
This page is a summary of: On Leveraging Large Language Models for Multilingual Intent Discovery, ACM Transactions on Management Information Systems, February 2025, ACM (Association for Computing Machinery),
DOI: 10.1145/3688400.
You can read the full text:
Contributors
The following have contributed to this page
