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.
Entropy-Enhanced Multimodal Attention Model for Scene-Aware Dialogue Generation
Teacher-Student Framework Enhanced Multi-domain Dialogue Generation
Few-Shot Dialogue Generation Without Annotated Data: A Transfer Learning Approach
M3D-GAN: Multi-Modal Multi-Domain Translation with Universal Attention
ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation
Multiple Generative Models Ensemble for Knowledge-Driven Proactive Human-Computer Dialogue Agent
DAL: Dual Adversarial Learning for Dialogue Generation
Automatic Conditional Generation of Personalized Social Media Short Texts
Personalizing Dialogue Agents via Meta-Learning
HUMBO: Bridging Response Generation and Facial Expression Synthesis
Theme-aware generation model for chinese lyrics
SuperChat: Dialogue Generation by Transfer Learning from Vision to Language using Two-dimensional Word Embedding and Pretrained ImageNet CNN Models
Text Generation from Knowledge Graphs with Graph Transformers
Knowledge-Grounded Response Generation with Deep Attentional Latent-Variable Model
Consistent Dialogue Generation with Self-supervised Feature Learning
Jointly Optimizing Diversity and Relevance in Neural Response Generation
Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models
Personalized Dialogue Generation with Diversified Traits
TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning
Another Diversity-Promoting Objective Function for Neural Dialogue Generation
Domain Agnostic Real-Valued Specificity Prediction
Wizard of Wikipedia: Knowledge-Powered Conversational agents
Importance of Search and Evaluation Strategies in Neural Dialogue Modeling
Towards Empathetic Open-domain Conversation Models: a New Benchmark and Dataset
A Dual-Attention Hierarchical Recurrent Neural Network for Dialogue Act Classification
Hierarchical Text Generation using an Outline
Improving Context Modelling in Multimodal Dialogue Generation
Learning Personas from Dialogue with Attentive Memory Networks
MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations
NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation
Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory
Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.