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
IDAS: Intent Discovery with Abstractive SummarizationCode1
Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent DiscoveryCode0
Going beyond research datasets: Novel intent discovery in the industry setting—0
A Clustering Framework for Unsupervised and Semi-supervised New Intent DiscoveryCode0
A Hybrid Architecture for Out of Domain Intent Detection and Intent DiscoveryCode1
Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent DiscoveryCode0
Generalized Intent Discovery: Learning from Open World Dialogue SystemCode0
Z-BERT-A: a zero-shot Pipeline for Unknown Intent detectionCode1
Intent Discovery for Enterprise Virtual Assistants: Applications of Utterance Embedding and Clustering to Intent Mining—0
Multimodal Intent Discovery from Livestream Videos—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