Wizard of Wikipedia: Knowledge-Powered Conversational agents
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.
Code (3)
Tasks
Dialogue GenerationSimilar Papers 제목 키워드 기반
Why and When: Understanding System Initiative during Conversational Collaborative Search
In the last decade, conversational search has attracted considerable attention. However, most research has focused on systems that can support a \emph{single} searcher. In this paper, we explore how systems can support \…
Conversational SearchContrastive Learning Reduces Hallucination in Conversations
Pre-trained language models (LMs) store knowledge in their parameters and can generate informative responses when used in conversational systems. However, LMs suffer from the problem of "hallucination:" they may generate…
Contrastive LearningHallucinationWizard of Tasks: A Novel Conversational Dataset for Solving Real-World Tasks in Conversational Settings
Conversational Task Assistants (CTAs) are conversational agents whose goal is to help humans perform real-world tasks. CTAs can help in exploring available tasks, answering task-specific questions and guiding users throu…
abstractive question answeringArticlesintent-classificationIntent Classification+1Extending Neural Generative Conversational Model using External Knowledge Sources
The use of connectionist approaches in conversational agents has been progressing rapidly due to the availability of large corpora. However current generative dialogue models often lack coherence and are content poor. Th…
Information Seeking in the Spirit of Learning: a Dataset for Conversational Curiosity
Open-ended human learning and information-seeking are increasingly mediated by digital assistants. However, such systems often ignore the user's pre-existing knowledge. Assuming a correlation between engagement and user …