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

Showing 110 of 42 papers

TitleStatusHype
New Intent Discovery with Pre-training and Contrastive LearningCode1
Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive LearningCode1
Intent Mining from past conversations for conversational agentCode1
Z-BERT-A: a zero-shot Pipeline for Unknown Intent detectionCode1
A Hybrid Architecture for Out of Domain Intent Detection and Intent DiscoveryCode1
IDAS: Intent Discovery with Abstractive SummarizationCode1
Benchmark Data and Evaluation Framework for Intent Discovery Around COVID-19 Vaccine HesitancyCode0
Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting FrameworkCode0
Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent DiscoveryCode0
Generalized Intent Discovery: Learning from Open World Dialogue SystemCode0
Show:102550
← PrevPage 1 of 5Next →

Benchmark Results

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