A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots
This addresses the challenge of building knowledge-aware chatbots for more accurate and interpretable conversational AI, though it appears incremental as it builds on existing matching networks.
The paper tackles the problem of response selection in retrieval-based chatbots by grounding conversations with background documents, resulting in significant improvements over state-of-the-art methods on two public datasets.
We present a document-grounded matching network (DGMN) for response selection that can power a knowledge-aware retrieval-based chatbot system. The challenges of building such a model lie in how to ground conversation contexts with background documents and how to recognize important information in the documents for matching. To overcome the challenges, DGMN fuses information in a document and a context into representations of each other, and dynamically determines if grounding is necessary and importance of different parts of the document and the context through hierarchical interaction with a response at the matching step. Empirical studies on two public data sets indicate that DGMN can significantly improve upon state-of-the-art methods and at the same time enjoys good interpretability.