Dialogue Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 13
- 보존된 평가 기록
- 20
Dialogue generation is the task of "understanding" natural language inputs - within natural language processing in order to produce output. The systems are usually intended for conversing with humans, for instance back and forth dialogue with a conversation agent like a chatbot. Some example benchmarks for this task (see others such as Natural Language Understanding) include FusedChat and Ubuntu DIalogue Corpus (UDC). Models can be evaluated via metrics such as BLEU, ROUGE, and METEOR albeit with challenges in terms of weak correlation with human judgement, that may be addressed by new ones like UnSupervised and Reference-free (USR) and Metric for automatic Unreferenced dialog evaluation (MaUde).
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
PLATO-K: Internal and External Knowledge Enhanced Dialogue Generation
Personalized Dialogue Generation with Persona-Adaptive Attention
Terminology-aware Medical Dialogue Generation
Transformer-Based Conditioned Variational Autoencoder for Dialogue Generation
There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning
Collaborative Reasoning on Multi-Modal Semantic Graphs for Video-Grounded Dialogue Generation
Towards Efficient Dialogue Pre-training with Transferable and Interpretable Latent Structure
Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection
Language Detoxification with Attribute-Discriminative Latent Space
DialoGen: Generalized Long-Range Context Representation for Dialogue Systems
SUMBot: Summarizing Context in Open-Domain Dialogue Systems
Measuring and Improving Semantic Diversity of Dialogue Generation
Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning
An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation
A Benchmark for Understanding and Generating Dialogue between Characters in Stories
Stateful Memory-Augmented Transformers for Efficient Dialogue Modeling
CrossDial: An Entertaining Dialogue Dataset of Chinese Crosstalk
Exploring Effective Information Utilization in Multi-Turn Topic-Driven Conversations
MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages
MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation
CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation
PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation
Follow Me: Conversation Planning for Target-driven Recommendation Dialogue Systems
Dynamically Retrieving Knowledge via Query Generation for Informative Dialogue Generation
Persona-Knowledge Dialogue Multi-Context Retrieval and Enhanced Decoding Methods
RT-KGD: Relation Transition Aware Knowledge-Grounded Dialogue Generation
Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation
Medical Dialogue Response Generation with Pivotal Information Recalling
Memory-Based Model Editing at Scale
Grounding in social media: An approach to building a chit-chat dialogue model
Learning to Generate Prompts for Dialogue Generation through Reinforcement Learning
CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI
Commonsense and Named Entity Aware Knowledge Grounded Dialogue Generation
Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation
DFM: Dialogue Foundation Model for Universal Large-Scale Dialogue-Oriented Task Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.