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.
ProsocialDialog: A Prosocial Backbone for Conversational Agents
BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla
Robust Task-Oriented Dialogue Generation with Contrastive Pre-training and Adversarial Filtering
Self-training with Two-phase Self-augmentation for Few-shot Dialogue Generation
Long-term Control for Dialogue Generation: Methods and Evaluation
A Simple Contrastive Learning Objective for Alleviating Neural Text Degeneration
Diversifying Neural Dialogue Generation via Negative Distillation
Semantic Diversity in Dialogue with Natural Language Inference
COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas
Building Knowledge-Grounded Dialogue Systems with Graph-Based Semantic Modeling
Anno-MI: A Dataset of Expert-Annotated Counselling Dialogues
Open-domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion
Emotion-Aware Transformer Encoder for Empathetic Dialogue Generation
SalesBot: Transitioning from Chit-Chat to Task-Oriented Dialogues
FaithDial: A Faithful Benchmark for Information-Seeking Dialogue
A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation
LingYi: Medical Conversational Question Answering System based on Multi-modal Knowledge Graphs
User-Centric Conversational Recommendation with Multi-Aspect User Modeling
A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond
Event Transition Planning for Open-ended Text Generation
DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation
Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation
AfriWOZ: Corpus for Exploiting Cross-Lingual Transferability for Generation of Dialogues in Low-Resource, African Languages
Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template Rewriting
Learning to Express in Knowledge-Grounded Conversation
PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Model
Exploiting Pairwise Mutual Information for Knowledge-Grounded Dialogue
TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge
Multi-Stage Prompting for Knowledgeable Dialogue Generation
Long Time No See! Open-Domain Conversation with Long-Term Persona Memory
An Interpretable Neuro-Symbolic Reasoning Framework for Task-Oriented Dialogue Generation
Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods
Deep Latent-Variable Models for Text Generation
VScript: Controllable Script Generation with Visual Presentation
AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.