Wizard of Wikipedia: Knowledge-Powered Conversational agents
This work addresses the challenge of building more engaging and informative AI assistants for general users by providing a benchmark for knowledge-grounded dialogue, though it is incremental in advancing existing methods.
The authors tackled the problem of creating open-domain conversational agents that effectively use knowledge by introducing a new dataset grounded in Wikipedia and designing models that retrieve and condition on this knowledge. Their best models achieved improved performance in knowledgeable discussions, as measured by both automatic metrics and human evaluations.
In open-domain dialogue intelligent agents should exhibit the use of knowledge, however there are few convincing demonstrations of this to date. The most popular sequence to sequence models typically "generate and hope" generic utterances that can be memorized in the weights of the model when mapping from input utterance(s) to output, rather than employing recalled knowledge as context. Use of knowledge has so far proved difficult, in part because of the lack of a supervised learning benchmark task which exhibits knowledgeable open dialogue with clear grounding. To that end we collect and release a large dataset with conversations directly grounded with knowledge retrieved from Wikipedia. We then design architectures capable of retrieving knowledge, reading and conditioning on it, and finally generating natural responses. Our best performing dialogue models are able to conduct knowledgeable discussions on open-domain topics as evaluated by automatic metrics and human evaluations, while our new benchmark allows for measuring further improvements in this important research direction.