# Automatic Discovery of Novel Intents & Domains from Text Utterances

arXiv: https://arxiv.org/abs/2006.01208 · HTML: https://mlsanity.com/paper/2006.01208/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2020.

## Built on by (most cited first, 5 of 5)

- [Generalized Category Discovery with Decoupled Prototypical Network](https://mlsanity.com/paper/2211.15115/) (2022)
- [Open-world Machine Learning: Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2105.13448/) (2021)
- [New Intent Discovery with Pre-training and Contrastive Learning](https://mlsanity.com/paper/2205.12914/) (2022)
- [Building the Intent Landscape of Real-World Conversational Corpora with Extractive Question-Answering Transformers](https://mlsanity.com/paper/2208.12886/) (2022)
- [OpenCML: End-to-End Framework of Open-world Machine Learning to Learn Unknown Classes Incrementally](https://mlsanity.com/paper/2511.19491/) (2025)

## Abstract (arXiv)

One of the primary tasks in Natural Language Understanding (NLU) is to recognize the intents as well as domains of users' spoken and written language utterances. Most existing research formulates this as a supervised classification problem with a closed-world assumption, i.e. the domains or intents to be identified are pre-defined or known beforehand. Real-world applications however increasingly encounter dynamic, rapidly evolving environments with newly emerging intents and domains, about which no information is known during model training. We propose a novel framework, ADVIN, to automatically discover novel domains and intents from large volumes of unlabeled data. We first employ an open classification model to identify all utterances potentially consisting of a novel intent. Next, we build a knowledge transfer component with a pairwise margin loss function. It learns discriminative deep features to group together utterances and discover multiple latent intent categories within them in an unsupervised manner. We finally hierarchically link mutually related intents into domains, forming an intent-domain taxonomy. ADVIN significantly outperforms baselines on three benchmark datasets, and real user utterances from a commercial voice-powered agent.