Papers with Code 아카이브
Intent Discovery
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 3
- 보존된 평가 기록
- 3
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
From Intent Discovery to Recognition with Topic Modeling and Synthetic Data
LANID: LLM-assisted New Intent Discovery
Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues
IntentGPT: Few-shot Intent Discovery with Large Language Models
KULCQ: An Unsupervised Keyword-based Utterance Level Clustering Quality Metric
Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agents
Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discovery
Assured Automatic Programming via Large Language Models
A Survey of Ontology Expansion for Conversational Understanding
Controllable Discovery of Intents: Incremental Deep Clustering Using Semi-Supervised Contrastive Learning
One Stone, Four Birds: A Comprehensive Solution for QA System Using Supervised Contrastive Learning
Towards Real-world Scenario: Imbalanced New Intent Discovery
RoNID: New Intent Discovery with Generated-Reliable Labels and Cluster-friendly Representations
New Intent Discovery with Attracting and Dispersing Prototype
IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery
A Diffusion Weighted Graph Framework for New Intent Discovery
Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPT
Continual Generalized Intent Discovery: Marching Towards Dynamic and Open-world Intent Recognition
Utilisation of open intent recognition models for customer support intent detection
IDAS: Intent Discovery with Abstractive Summarization
Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery
Going beyond research datasets: Novel intent discovery in the industry setting
A Clustering Framework for Unsupervised and Semi-supervised New Intent Discovery
A Hybrid Architecture for Out of Domain Intent Detection and Intent Discovery
Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery
Generalized Intent Discovery: Learning from Open World Dialogue System
Z-BERT-A: a zero-shot Pipeline for Unknown Intent detection
New Intent Discovery with Pre-training and Contrastive Learning
Benchmark Data and Evaluation Framework for Intent Discovery Around COVID-19 Vaccine Hesitancy
TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition
Open Intent Discovery through Unsupervised Semantic Clustering and Dependency Parsing
Intent Mining from past conversations for conversational agent
Towards Open Intent Discovery for Conversational Text
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.