Zero-Resource Knowledge-Grounded Dialogue Generation
This reduces the cost and data requirements for building knowledge-grounded dialogue systems, addressing a bottleneck in conversational AI, though it is an incremental improvement over existing methods.
The paper tackles the problem of generating knowledge-grounded dialogues without requiring paired context-knowledge-response triples for training, proposing a variational model that uses independent dialogue and knowledge corpora. It achieves comparable performance to state-of-the-art methods on three benchmarks, showing good generalization across topics and datasets.
While neural conversation models have shown great potentials towards generating informative and engaging responses via introducing external knowledge, learning such a model often requires knowledge-grounded dialogues that are difficult to obtain. To overcome the data challenge and reduce the cost of building a knowledge-grounded dialogue system, we explore the problem under a zero-resource setting by assuming no context-knowledge-response triples are needed for training. To this end, we propose representing the knowledge that bridges a context and a response and the way that the knowledge is expressed as latent variables, and devise a variational approach that can effectively estimate a generation model from a dialogue corpus and a knowledge corpus that are independent with each other. Evaluation results on three benchmarks of knowledge-grounded dialogue generation indicate that our model can achieve comparable performance with state-of-the-art methods that rely on knowledge-grounded dialogues for training, and exhibits a good generalization ability over different topics and different datasets.