Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
arXiv:2010.08824
Abstract
We study knowledge-grounded dialogue generation with pre-trained language models. To leverage the redundant external knowledge under capacity constraint, we propose equipping response generation defined by a pre-trained language model with a knowledge selection module, and an unsupervised approach to jointly optimizing knowledge selection and response generation with unlabeled dialogues. Empirical results on two benchmarks indicate that our model can significantly outperform state-of-the-art methods in both automatic evaluation and human judgment.
arXiv commentAccepted by EMNLP 2020
References in corpus (26)
- Sequence to Sequence Learning with Neural Networks
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Convolutional Sequence to Sequence Learning
- Cross-lingual Language Model Pretraining
- A Neural Conversational Model
- VL-BERT: Pre-training of Generic Visual-Linguistic Representations
- Wizard of Wikipedia: Knowledge-Powered Conversational agents
- How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
- MASS: Masked Sequence to Sequence Pre-training for Language Generation
- Topic Aware Neural Response Generation
- TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
- Towards a Human-like Open-Domain Chatbot
- Personalizing Dialogue Agents: I have a dog, do you have pets too?
- Understanding the Behaviors of BERT in Ranking
- Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation
- Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
- Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
- DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
- Low-Resource Knowledge-Grounded Dialogue Generation
- Zero-Resource Knowledge-Grounded Dialogue Generation
- Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information
- What makes a good conversation? How controllable attributes affect human judgments
- Learning to Select Knowledge for Response Generation in Dialog Systems
- Incremental Transformer with Deliberation Decoder for Document Grounded Conversations
- A Dataset for Document Grounded Conversations
- Neural Response Generation with Meta-Words