IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery
Bhavuk Singhal, Ashim Gupta, V P Shivasankaran, Amrith Krishna
Abstract
Identifying intents from dialogue utterances forms an integral component of task-oriented dialogue systems. Intent-related tasks are typically formulated either as a classification task, where the utterances are classified into predefined categories or as a clustering task when new and previously unknown intent categories need to be discovered from these utterances. Further, the intent classification may be modeled in a multiclass (MC) or multilabel (ML) setup. While typically these tasks are modeled as separate tasks, we propose IntenDD a unified approach leveraging a shared utterance encoding backbone. IntenDD uses an entirely unsupervised contrastive learning strategy for representation learning, where pseudo-labels for the unlabeled utterances are generated based on their lexical features. Additionally, we introduce a two-step post-processing setup for the classification tasks using modified adsorption. Here, first, the residuals in the training data are propagated followed by smoothing the labels both modeled in a transductive setting. Through extensive evaluations on various benchmark datasets, we find that our approach consistently outperforms competitive baselines across all three tasks. On average, IntenDD reports percentage improvements of 2.32 %, 1.26 %, and 1.52 % in their respective metrics for few-shot MC, few-shot ML, and the intent discovery tasks respectively.- Anthology ID:
- 2023.findings-emnlp.947
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 14204–14216
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.947
- DOI:
- 10.18653/v1/2023.findings-emnlp.947
- Cite (ACL):
- Bhavuk Singhal, Ashim Gupta, V P Shivasankaran, and Amrith Krishna. 2023. IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 14204–14216, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery (Singhal et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2023.findings-emnlp.947.pdf