https://github.com/knalin55/leeets-dial
공식 코드LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Dialogue is notoriously hard to evaluate. Past approaches have used human evaluation.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems
ConfNet2Seq: Full Length Answer Generation from Spoken Questions
A Contrastive Learning Approach to Mitigate Bias in Speech Models
"Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding
"KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding
Agentic Feedback Loop Modeling Improves Recommendation and User Simulation
Unsupervised Conversation Disentanglement through Co-Training
Semi-Supervised Variational Reasoning for Medical Dialogue Generation
MultiMed: Multilingual Medical Speech Recognition via Attention Encoder Decoder
CTRLStruct: Dialogue Structure Learning for Open-Domain Response Generation
A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets
UNO-DST: Leveraging Unlabelled Data in Zero-Shot Dialogue State Tracking
OpenSLU: A Unified, Modularized, and Extensible Toolkit for Spoken Language Understanding
Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings
EnSToM: Enhancing Dialogue Systems with Entropy-Scaled Steering Vectors for Topic Maintenance
Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking
User-Centric Conversational Recommendation with Multi-Aspect User Modeling
A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond
Unsupervised Post-processing of Word Vectors via Conceptor Negation
Text is no more Enough! A Benchmark for Profile-based Spoken Language Understanding
Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models
Modeling Content-Emotion Duality via Disentanglement for Empathetic Conversation
RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL
MedDG: An Entity-Centric Medical Consultation Dataset for Entity-Aware Medical Dialogue Generation
Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.