"What is on your mind?" Automated Scoring of Mindreading in Childhood and Early Adolescence

11/16/2020

∙

by   Venelin Kovatchev, et al.

∙

0

∙

share

In this paper we present the first work on the automated scoring of mindreading ability in middle childhood and early adolescence. We create MIND-CA, a new corpus of 11,311 question-answer pairs in English from 1,066 children aged 7 to 14. We perform machine learning experiments and carry out extensive quantitative and qualitative evaluation. We obtain promising results, demonstrating the applicability of state-of-the-art NLP solutions to a new domain and task.