@inproceedings{behr-2024-elc,
    title = "{ELC}-{P}arser{BERT}: Low-Resource Language Modeling Utilizing a Parser Network With {ELC}-{BERT}",
    author = "Behr, Rufus",
    editor = "Hu, Michael Y.  and
      Mueller, Aaron  and
      Ross, Candace  and
      Williams, Adina  and
      Linzen, Tal  and
      Zhuang, Chengxu  and
      Choshen, Leshem  and
      Cotterell, Ryan  and
      Warstadt, Alex  and
      Wilcox, Ethan Gotlieb",
    booktitle = "The 2nd BabyLM Challenge at the 28th Conference on Computational Natural Language Learning",
    month = nov,
    year = "2024",
    address = "Miami, FL, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.conll-babylm.11/",
    pages = "140--146",
    abstract = "This paper investigates the effect of including a parser network, which produces syntactic heights and distances to perform unsupervised parsing, in the Every Layer Counts BERT (ELC-BERT) architecture trained on 10M tokens for the 2024 BabyLM challenge. The parser network`s inclusion in this setup shows little or no improvement over the ELC-BERT baseline for the BLiMP and GLUE evaluation, but, in particular domains of the EWoK evaluation framework, its inclusion shows promise for improvement and raises interesting questions about its effect on learning different concepts."
}