no code implementations • EACL (BEA) 2021 • Elma Kerz, Daniel Wiechmann, Yu Qiao, Emma Tseng, Marcus Ströbel
The key to the present paper is the combined use of what we refer to as ‘complexity contours’, a series of measurements of indices of L2 proficiency obtained by a computational tool that implements a sliding window technique, and recurrent neural network (RNN) classifiers that adequately capture the sequential information in those contours.