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.
Bilevel Scheduled Sampling for Dialogue Generation
RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
TARJAMAT: Evaluation of Bard and ChatGPT on Machine Translation of Ten Arabic Varieties
Dataflow Dialogue Generation
ZRIGF: An Innovative Multimodal Framework for Zero-Resource Image-Grounded Dialogue Generation
DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering
Does Collaborative Human-LM Dialogue Generation Help Information Extraction from Human Dialogues?
Attribute Controlled Dialogue Prompting
DialoGPS: Dialogue Path Sampling in Continuous Semantic Space for Data Augmentation in Multi-Turn Conversations
Enhancing Dialogue Generation via Dynamic Graph Knowledge Aggregation
MindDial: Belief Dynamics Tracking with Theory-of-Mind Modeling for Situated Neural Dialogue Generation
KnowPrefix-Tuning: A Two-Stage Prefix-Tuning Framework for Knowledge-Grounded Dialogue Generation
Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation
HAUSER: Towards Holistic and Automatic Evaluation of Simile Generation
MidMed: Towards Mixed-Type Dialogues for Medical Consultation
Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference
VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions
Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation
Medical Dialogue Generation via Dual Flow Modeling
GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking
Contextual Knowledge Learning For Dialogue Generation
Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response
Cross-lingual Data Augmentation for Document-grounded Dialog Systems in Low Resource Languages
Dolphin: A Challenging and Diverse Benchmark for Arabic NLG
RefGPT: Dialogue Generation of GPT, by GPT, and for GPT
Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge
Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization
Enhancing Personalized Dialogue Generation with Contrastive Latent Variables: Combining Sparse and Dense Persona
PlugMed: Improving Specificity in Patient-Centered Medical Dialogue Generation using In-Context Learning
DiffuSIA: A Spiral Interaction Architecture for Encoder-Decoder Text Diffusion
SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation
IMAD: IMage-Augmented multi-modal Dialogue
Parameter-Efficient Fine-Tuning with Layer Pruning on Free-Text Sequence-to-Sequence Modeling
NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist
Prompt Learning to Mitigate Catastrophic Forgetting in Cross-lingual Transfer for Open-domain Dialogue Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.