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.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/Makbari1997/VAE-KPCA-HDBSCAN

공식 코드

A Hybrid Architecture for Out of Domain Intent Detection and Intent Discovery

https://github.com/ajaychatterjee/IntentMining

공식 코드

Intent Mining from past conversations for conversational agent

https://github.com/bowang-rw-02/scl-one-for-four

공식 코드

One Stone, Four Birds: A Comprehensive Solution for QA System Using Supervised Contrastive Learning

https://github.com/dymanne123/PLPCL

공식 코드

Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discovery

https://github.com/floatsdsds/lanid

공식 코드

LANID: LLM-assisted New Intent Discovery

https://github.com/gt4sd/zberta

공식 코드

Z-BERT-A: a zero-shot Pipeline for Unknown Intent detection

https://github.com/gt4sd/zero-shot-bert-adapters

공식 코드

Z-BERT-A: a zero-shot Pipeline for Unknown Intent detection

https://github.com/ibm/vira-intent-discovery

공식 코드

Benchmark Data and Evaluation Framework for Intent Discovery Around COVID-19 Vaccine Hesitancy

https://github.com/maarten-deraedt/idas-intent-discovery-with-abstract-summarization

공식 코드

IDAS: Intent Discovery with Abstractive Summarization

https://github.com/myt517/gid_benchmark

공식 코드

Generalized Intent Discovery: Learning from Open World Dialogue System

https://github.com/myt517/kcod

공식 코드

Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery

https://github.com/ppfliu/open-intent-discovery

공식 코드

Open Intent Discovery through Unsupervised Semantic Clustering and Dependency Parsing

https://github.com/smileix/cpp

공식 코드

Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting Framework

https://github.com/songxiaoshuai/CGID

공식 코드

Continual Generalized Intent Discovery: Marching Towards Dynamic and Open-world Intent Recognition

https://github.com/songxiaoshuai/OOD-Evaluation

공식 코드

Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPT

https://github.com/songxiaoshuai/dpl

공식 코드

Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery

https://github.com/thuiar/textoir

공식 코드

TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition

https://github.com/thuiar/textoir-demo

공식 코드

TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition

https://github.com/yibai-shi/dwgf

공식 코드

A Diffusion Weighted Graph Framework for New Intent Discovery

https://github.com/zhang-yu-wei/mtp-clnn

공식 코드

New Intent Discovery with Pre-training and Contrastive Learning

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.