SOTAVerified

Intent Discovery

Given a set of labelled and unlabelled utterances, the idea is to identify existing (known) intents and potential (new intents) intents. This method can be utilised in conversational system setting.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–30 of 42 papers

TitleStatusHype
A Diffusion Weighted Graph Framework for New Intent DiscoveryCode0
UNICON: Unsupervised Intent Discovery via Semantic-level Contrastive Learning—0
Assured Automatic Programming via Large Language Models—0
A Survey of Ontology Expansion for Conversational Understanding—0
Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agents—0
Controllable Discovery of Intents: Incremental Deep Clustering Using Semi-Supervised Contrastive Learning—0
Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues—0
Going beyond research datasets: Novel intent discovery in the industry setting—0
IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery—0
Intent Detection and Discovery from User Logs via Deep Semi-Supervised Contrastive Clustering—0
Show:102550
← PrevPage 3 of 5Next →
All datasetsATISPersian-ATISSNIPS

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1k-PCA + HDBSCANARI74.94—Unverified
#ModelMetricClaimedVerifiedStatus
1k-PCA + HDBSCANARI11.97—Unverified
#ModelMetricClaimedVerifiedStatus
1k-PCA + HDBSCANARI59.23—Unverified