Identifying user intents from natural language utterances is a crucial step in conversational systems that has been extensively studied as a supervised classification problem. However, in practice, new intents emerge after deploying an intent detection model. Thus, these models should seamlessly adapt and classify utterances with both seen and unseen intents - unseen intents emerge after deployment and they do not have training data. The few existing models that target this setting rely heavily on the training data of seen intents and consequently overfit to these intents, resulting in a bias to misclassify utterances with unseen intents into seen ones. We propose RIDE: an intent detection model that leverages commonsense knowledge in an unsupervised fashion to overcome the issue of training data scarcity. RIDE computes robust and generalizable relationship meta-features that capture deep semantic relationships between utterances and intent labels; these features are computed by considering how the concepts in an utterance are linked to those in an intent label via commonsense knowledge. Our extensive experimental analysis on three widely-used intent detection benchmarks shows that relationship meta-features significantly improve the detection of both seen and unseen intents and that RIDE outperforms the state-of-the-art models.
|Title of host publication||SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval|
|Number of pages||5|
|State||Published - Jul 11 2021|
|Event||44th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2021 - Virtual, Online, Canada|
Duration: Jul 11 2021 → Jul 15 2021
|Name||SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval|
|Conference||44th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2021|
|Period||7/11/21 → 7/15/21|
Bibliographical noteFunding Information:
This work is supported in part by the National Science Foundation (NSF) under grants IIS-1838222 and IIS-1901379.
© 2021 Owner/Author.
- generalized zero-shot learning
- natural language processing
- natural language understanding
- out of domain intent detection
ASJC Scopus subject areas
- Computer Graphics and Computer-Aided Design
- Information Systems