Intent Discovery
3개 벤치마크 · 논문 45편 · 이 태스크의 논문 보기 →
Benchmarks
Most implemented
Z-BERT-A: a zero-shot Pipeline for Unknown Intent detection
Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting Framework
LANID: LLM-assisted New Intent Discovery
Papers
SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces
Large Language Model (LLM)-based agents increasingly automate software engineering tasks through reusable skills, natural-language instruction documents that guide planning and execution. Open skill marketplaces enable u…
Intent DiscoveryTextClusterLab: An Integrated Framework for Reliable Text Clustering Studies
In recent years, text clustering has become a critical technique for applications including intent discovery, topic mining, and recommendation systems. However, evaluating text clustering algorithms remains challenging s…
Recommendation SystemsIntent DiscoveryText ClusteringNILC: Discovering New Intents with LLM-assisted Clustering
New intent discovery (NID) seeks to recognize both new and known intents from unlabeled user utterances, which finds prevalent use in practical dialogue systems. Existing works towards NID mainly adopt a cascaded archite…
Intent DiscoveryIntegration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting Framework
Intent detection aims to identify user intents from natural language inputs, where supervised methods rely heavily on labeled in-domain (IND) data and struggle with out-of-domain (OOD) intents, limiting their practical a…
Domain AdaptationIntent DetectionIntent DiscoveryFrom Intent Discovery to Recognition with Topic Modeling and Synthetic Data
Understanding and recognizing customer intents in AI systems is crucial, particularly in domains characterized by short utterances and the cold start problem, where recommender systems must include new products or servic…
DiversityIntent DiscoveryIntent RecognitionRecommendation Systems+1LANID: LLM-assisted New Intent Discovery
Task-oriented Dialogue Systems (TODS) often face the challenge of encountering new intents. New Intent Discovery (NID) is a crucial task that aims to identify these novel intents while maintaining the capability to recog…
Intent DiscoveryTask-Oriented Dialogue SystemsTriplet