Learning from Dialogue after Deployment: Feed Yourself, Chatbot!

Pierre-Emmanuel Mazaré
Pierre-Emmanuel Mazaré

Meeting of the Association for Computational Linguistics, Volume abs/1901.05415, 2019.

Cited by: 19|Bibtex|Views143
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

The majority of conversations a dialogue agent sees over its lifetime occur after it has already been trained and deployed, leaving a vast store of potential training signal untapped. In this work, we propose the self-feeding chatbot, a dialogue agent with the ability to extract new training examples from the conversations it participates...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments