Incorporating Relevant Knowledge in Context Modeling and Response Generation
arXiv:1811.03729
Abstract
To sustain engaging conversation, it is critical for chatbots to make good use of relevant knowledge. Equipped with a knowledge base, chatbots are able to extract conversation-related attributes and entities to facilitate context modeling and response generation. In this work, we distinguish the uses of attribute and entity and incorporate them into the encoder-decoder architecture in different manners. Based on the augmented architecture, our chatbot, namely Mike, is able to generate responses by referring to proper entities from the collected knowledge. To validate the proposed approach, we build a movie conversation corpus on which the proposed approach significantly outperforms other four knowledge-grounded models.
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Sequence to Sequence Learning with Neural Networks
- DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
- Enriching Word Vectors with Subword Information
- Incorporating Copying Mechanism in Sequence-to-Sequence Learning
- Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention
- Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
- End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
- Flexible End-to-End Dialogue System for Knowledge Grounded Conversation
- From Eliza to XiaoIce: Challenges and Opportunities with Social Chatbots
- LSTM based Conversation Models
- A Conditional Variational Framework for Dialog Generation
- Latent Intention Dialogue Models
- Reference-Aware Language Models