Where is the context? – A critique of recent dialogue datasets

04/22/2020
by   Johannes E. M. Mosig, et al.
0

Recent dialogue datasets like MultiWOZ 2.1 and Taskmaster-1 constitute some of the most challenging tasks for present-day dialogue models and, therefore, are widely used for system evaluation. We identify several issues with the above-mentioned datasets, such as history independence, strong knowledge base dependence, and ambiguous system responses. Finally, we outline key desiderata for future datasets that we believe would be more suitable for the construction of conversational artificial intelligence.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset