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 11–20 of 42 papers

TitleStatusHype
Controllable Discovery of Intents: Incremental Deep Clustering Using Semi-Supervised Contrastive Learning—0
One Stone, Four Birds: A Comprehensive Solution for QA System Using Supervised Contrastive LearningCode0
Towards Real-world Scenario: Imbalanced New Intent DiscoveryCode0
RoNID: New Intent Discovery with Generated-Reliable Labels and Cluster-friendly Representations—0
New Intent Discovery with Attracting and Dispersing Prototype—0
IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery—0
A Diffusion Weighted Graph Framework for New Intent DiscoveryCode0
Continual Generalized Intent Discovery: Marching Towards Dynamic and Open-world Intent RecognitionCode0
Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPTCode0
Utilisation of open intent recognition models for customer support intent detection—0
Show:102550
← PrevPage 2 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