Wizard of Wikipedia: Knowledge-Powered Conversational agents

by   Emily Dinan, et al.

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.


Automatic Evaluation of Neural Personality-based Chatbots

Stylistic variation is critical to render the utterances generated by co...

Grounding in social media: An approach to building a chit-chat dialogue model

Building open-domain dialogue systems capable of rich human-like convers...

Extending Neural Generative Conversational Model using External Knowledge Sources

The use of connectionist approaches in conversational agents has been pr...

Open-domain Topic Identification of Out-of-domain Utterances using Wikipedia

Users of spoken dialogue systems (SDS) expect high quality interactions ...

Contrastive Learning Reduces Hallucination in Conversations

Pre-trained language models (LMs) store knowledge in their parameters an...

Personalizing Dialogue Agents: I have a dog, do you have pets too?

Chit-chat models are known to have several problems: they lack specifici...

Deploying Lifelong Open-Domain Dialogue Learning

Much of NLP research has focused on crowdsourced static datasets and the...

Please sign up or login with your details

Forgot password? Click here to reset