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.
Dialogue Planning via Brownian Bridge Stochastic Process for Goal-directed Proactive Dialogue
Controllable Mixed-Initiative Dialogue Generation through Prompting
White-Box Multi-Objective Adversarial Attack on Dialogue Generation
U-NEED: A Fine-grained Dataset for User Needs-Centric E-commerce Conversational Recommendation
Semantic Space Grounded Weighted Decoding for Multi-Attribute Controllable Dialogue Generation
Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory
An Empirical Study of Multitask Learning to Improve Open Domain Dialogue Systems
The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents
When Crowd Meets Persona: Creating a Large-Scale Open-Domain Persona Dialogue Corpus
Elastic Weight Removal for Faithful and Abstractive Dialogue Generation
G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
How do decoding algorithms distribute information in dialogue responses?
Deep RL with Hierarchical Action Exploration for Dialogue Generation
Heterogeneous-Branch Collaborative Learning for Dialogue Generation
Learning towards Selective Data Augmentation for Dialogue Generation
X-ReCoSa: Multi-Scale Context Aggregation For Multi-Turn Dialogue Generation
CTRLStruct: Dialogue Structure Learning for Open-Domain Response Generation
Almanac: Retrieval-Augmented Language Models for Clinical Medicine
GLM-Dialog: Noise-tolerant Pre-training for Knowledge-grounded Dialogue Generation
Topic-switch adapted Japanese Dialogue System based on PLATO-2
CAB: Empathetic Dialogue Generation with Cognition, Affection and Behavior
Commonsense-Aware Prompting for Controllable Empathetic Dialogue Generation
Response-act Guided Reinforced Dialogue Generation for Mental Health Counseling
GE-Blender: Graph-Based Knowledge Enhancement for Blender
Learning to Memorize Entailment and Discourse Relations for Persona-Consistent Dialogues
Improving a sequence-to-sequence nlp model using a reinforcement learning policy algorithm
SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization
CausalDialogue: Modeling Utterance-level Causality in Conversations
Ontologically Faithful Generation of Non-Player Character Dialogues
SESCORE2: Learning Text Generation Evaluation via Synthesizing Realistic Mistakes
InferEM: Inferring the Speaker's Intention for Empathetic Dialogue Generation
Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables
Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder
CDialog: A Multi-turn Covid-19 Conversation Dataset for Entity-Aware Dialog Generation
Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.