Exploring the impact of dependency length on learnability

Ayla Karakaş

Published: 03 Oct 2025, Last Modified: 04 Nov 2025CPL 2025 PosterEveryoneRevisionsBibTeXCC BY 4.0
Keywords: language acquisition, length generalization, data complexity, LSTM
TL;DR: LSTMs fail to show computational support for the "less is more" hypothesis, likely due to fundamental architectural limitations that challenge the analogy between network training and human language acquisition.
Submission Number: 32