https://github.com/caoyu-noob/embedding_augmentation
공식 코드Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentation
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.
Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentation
DeepStruct: Pretraining of Language Models for Structure Prediction
Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization
Learning to Memorize Entailment and Discourse Relations for Persona-Consistent Dialogues
COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas
Dialogue State Tracking with a Language Model using Schema-Driven Prompting
Diversifying Dialogue Generation with Non-Conversational Text
KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems
CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation
Don't Lose Yourself! Empathetic Response Generation via Explicit Self-Other Awareness
Evaluating Dialogue Generation Systems via Response Selection
Rethinking the Evaluation of Dialogue Systems: Effects of User Feedback on Crowdworkers and LLMs
Efficient Dialogue State Tracking by Selectively Overwriting Memory
Two-stage Textual Knowledge Distillation for End-to-End Spoken Language Understanding
Domain Transfer in Dialogue Systems without Turn-Level Supervision
Dialogue Benchmark Generation from Knowledge Graphs with Cost-Effective Retrieval-Augmented LLMs
EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use
Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems
Strategic Dialogue Management via Deep Reinforcement Learning
Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptation
BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing
Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systems
Shift-Reduce Task-Oriented Semantic Parsing with Stack-Transformers
M2H2: A Multimodal Multiparty Hindi Dataset For Humor Recognition in Conversations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.