Incorporating Relevant Knowledge in Context Modeling and Response Generation
This addresses the problem of improving chatbot engagement for users by better utilizing knowledge, though it appears incremental as it builds on existing knowledge-grounded models with architectural modifications.
The paper tackled the problem of making chatbots sustain engaging conversations by incorporating relevant knowledge from a knowledge base, distinguishing between attribute and entity usage in encoder-decoder architectures, and resulted in their chatbot Mike significantly outperforming four other knowledge-grounded models on a movie conversation corpus.
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.