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.
Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation
Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts
Self-Attention-Based Message-Relevant Response Generation for Neural Conversation Model
Zero-Shot Dialog Generation with Cross-Domain Latent Actions
Polite Dialogue Generation Without Parallel Data
Modeling Psychotherapy Dialogues with Kernelized Hashcode Representations: A Nonparametric Information-Theoretic Approach
Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation
Improving Variational Encoder-Decoders in Dialogue Generation
DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text
Personalizing Dialogue Agents: I have a dog, do you have pets too?
End-to-end Adversarial Learning for Generative Conversational Agents
Towards Automatic Generation of Entertaining Dialogues in Chinese Crosstalks
Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation
IDK Cascades: Fast Deep Learning by Learning not to Overthink
Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
Data Distillation for Controlling Specificity in Dialogue Generation
Latent Variable Dialogue Models and their Diversity
Adversarial Learning for Neural Dialogue Generation
Deep Active Learning for Dialogue Generation
Reference-Aware Language Models
Deep Reinforcement Learning for Dialogue Generation
Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
Neural Machine Translation by Jointly Learning to Align and Translate
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.