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 2642 of 42 papers

TitleStatusHype
Utilisation of open intent recognition models for customer support intent detection0
Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent DiscoveryCode0
Going beyond research datasets: Novel intent discovery in the industry setting0
A Clustering Framework for Unsupervised and Semi-supervised New Intent DiscoveryCode0
Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent DiscoveryCode0
Generalized Intent Discovery: Learning from Open World Dialogue SystemCode0
Multimodal Intent Discovery from Livestream Videos0
Intent Detection and Discovery from User Logs via Deep Semi-Supervised Contrastive Clustering0
Intent Discovery for Enterprise Virtual Assistants: Applications of Utterance Embedding and Clustering to Intent Mining0
Benchmark Data and Evaluation Framework for Intent Discovery Around COVID-19 Vaccine HesitancyCode0
UNICON: Unsupervised Intent Discovery via Semantic-level Contrastive Learning0
Semi-supervised Intent Discovery with Contrastive Learning0
TEXTOIR: An Integrated and Visualized Platform for Text Open Intent RecognitionCode0
Unknown Intent Detection Using Multi-Objective Optimization on Deep Learning Classifiers0
Open Intent Discovery through Unsupervised Semantic Clustering and Dependency ParsingCode0
Intent Discovery With Or Without Labeled Data Using Dependency Parser0
Towards Open Intent Discovery for Conversational Text0
Show:102550
← PrevPage 2 of 2Next →

Benchmark Results

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