SOTAVerified

Open Intent Discovery

Open intent discovery aims to leverage limited prior knowledge of known intents to find fine-grained known and open intent-wise clusters.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–7 of 7 papers

TitleStatusHype
Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent DiscoveryCode0
Intent Detection and Discovery from User Logs via Deep Semi-Supervised Contrastive Clustering—0
TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition—0
Open Intent Discovery through Unsupervised Semantic Clustering and Dependency ParsingCode0
Discovering New Intents with Deep Aligned ClusteringCode1
Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster RefinementCode0
Towards Open Intent Discovery for Conversational Text—0
Show:102550
All datasetsBANKING77CLINC150SNIPSStackoverflowATISDBpedia

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DSSCCACC94.87—Unverified
2CDAC+ACC93.63—Unverified