* If you want to update the article please login/register
The approach is based on human evaluators administering a targeted oral exam to a test device and reporting their subjective assessment of the system's results on each test issue. The proposed metrics reveal valuable insight into the relative strengths and weaknesses of these applications, according to one instantiation of the test being carried out on two publicly accessible dialog systems and a human.
Source link: https://doi.org/10.1609/aaai.v30i1.10060
* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions