Personalizing Dialogue Agents: I have a dog, do you have pets too?
This work addresses the issue of impersonal and inconsistent dialogue agents for users of conversational AI, though it is incremental as it builds on existing chit-chat models.
The paper tackled the problem of unengaging chit-chat models by conditioning dialogue agents on profile information, resulting in improved dialogues measured by next utterance prediction and the ability to predict interlocutor profiles.
Chit-chat models are known to have several problems: they lack specificity, do not display a consistent personality and are often not very captivating. In this work we present the task of making chit-chat more engaging by conditioning on profile information. We collect data and train models to (i) condition on their given profile information; and (ii) information about the person they are talking to, resulting in improved dialogues, as measured by next utterance prediction. Since (ii) is initially unknown our model is trained to engage its partner with personal topics, and we show the resulting dialogue can be used to predict profile information about the interlocutors.