Year: 2023
Type: conference-paper
Abstract: This paper details the work of the University of Groningen for the BabyLM Challenge. We follow the idea that, like babies, language models should be introduced to simpler concepts first and build off of that knowledge to understand more complex concepts. We examine this strategy of simple-then-complex through a variety of lenses, namely context size, vocabulary, and overall linguistic complexity of the data. We find that only one, context size, is truly beneficial to training a language model. However this simple change to context size gives us improvements of 2 points on average on (Super)GLUE tasks, 1 point on MSGS tasks, and 12\% on average on BLiMP tasks. Our context-limited model outperforms the baseline that was trained on 10$\times$ the amount of data.
Source: BabyLM Challenge
Authors: Lukas Edman, Lisa Bylinina
Institution: University of Groningen
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: Rijksuniversiteit Groningen
OpenAlex ID: W4389524063