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.
Survey of Hallucination in Natural Language Generation
Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation
Taming Repetition in Dialogue Generation
Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation
DG2: Data Augmentation Through Document Grounded Dialogue Generation
ValueNet: A New Dataset for Human Value Driven Dialogue System
Partner Personas Generation for Diverse Dialogue Generation
DLVGen: A Dual Latent Variable Approach to Personalized Dialogue Generation
DSBERT:Unsupervised Dialogue Structure learning with BERT
Response Generation with Context-Aware Prompt Learning
Adaptive Bridge between Training and Inference for Dialogue
Multimodal Dialogue Response Generation
RecInDial: A Unified Framework for Conversational Recommendation with Pretrained Language Models
A Speaker-aware Parallel Hierarchical Attentive Encoder-Decoder Model for Multi-turn Dialogue Generation
OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts
Learning Neural Templates for Recommender Dialogue System
Simulated Annealing for Emotional Dialogue Systems
PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation
Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes
Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation
Constructing Emotion Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation
Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimization
Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward
Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generation
Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation
Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems
A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation
Fusing task-oriented and open-domain dialogues in conversational agents
Empathetic Dialogue Generation with Pre-trained RoBERTa-GPT2 and External Knowledge
SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks
$\infty$-former: Infinite Memory Transformer
ReMeDi: Resources for Multi-domain, Multi-service, Medical Dialogues
Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts
MMChat: Multi-Modal Chat Dataset on Social Media
Generating Personalized Dialogue via Multi-Task Meta-Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.