Evaluating Agent Interactions Through Episodic Knowledge Graphs

09/22/2022
by   Selene Báez Santamaría, et al.
0

We present a new method based on episodic Knowledge Graphs (eKGs) for evaluating (multimodal) conversational agents in open domains. This graph is generated by interpreting raw signals during conversation and is able to capture the accumulation of knowledge over time. We apply structural and semantic analysis of the resulting graphs and translate the properties into qualitative measures. We compare these measures with existing automatic and manual evaluation metrics commonly used for conversational agents. Our results show that our Knowledge-Graph-based evaluation provides more qualitative insights into interaction and the agent's behavior.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset