ChapGTP, ILLC’s Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formation

Open Access
Authors
Publication date 2023
Host editors
  • A. Warstadt
  • A. Mueller
  • L. Choshen
  • E. Wilcox
  • C. Zhuang
  • J. Ciro
  • R. Mosquera
  • B. Paranjabe
  • A. Williams
  • T. Linzen
  • R. Cotterell
Book title Findings of the BabyLM Challenge: Sample-efficient pretraining on developmentally plausible corpora
ISBN (electronic)
  • 9781952148026
Event BabyLM Challenge at the 27th Conference on Computational Natural Language Learning
Pages (from-to) 74-85
Publisher Stroudsburg, PA: Association for Computational Linguistics
Organisations
  • Interfacultary Research - Institute for Logic, Language and Computation (ILLC)
Abstract We present the submission of the ILLC at the University of Amsterdam to the BabyLM challenge (Warstadt et al., 2023), in the strict-small track. Our final model, ChapGTP, is a masked language model that was trained for 200 epochs, aided by a novel data augmentation technique called Automatic Task Formation. We discuss in detail the performance of this model on the three evaluation suites: BLiMP, (Super)GLUE, and MSGS. Furthermore, we present a wide range of methods that were ultimately not included in the model, but may serve as inspiration for training LMs in low-resource settings.
Document type Conference contribution
Language English
Published at https://doi.org/10.18653/v1/2023.conll-babylm.6
Downloads
2023.conll-babylm.6 (Final published version)
Permalink to this page
Back