@inproceedings{kementchedjhieva-lopez-2018-indicatements,
    title = "{\textquoteleft}Indicatements' that character language models learn {E}nglish morpho-syntactic units and regularities",
    author = "Kementchedjhieva, Yova  and
      Lopez, Adam",
    editor = "Linzen, Tal  and
      Chrupa{\l}a, Grzegorz  and
      Alishahi, Afra",
    booktitle = "Proceedings of the 2018 {EMNLP} Workshop {B}lackbox{NLP}: Analyzing and Interpreting Neural Networks for {NLP}",
    month = nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/W18-5417/",
    doi = "10.18653/v1/W18-5417",
    pages = "145--153",
    abstract = "Character language models have access to surface morphological patterns, but it is not clear whether or \textit{how} they learn abstract morphological regularities. We instrument a character language model with several probes, finding that it can develop a specific unit to identify word boundaries and, by extension, morpheme boundaries, which allows it to capture linguistic properties and regularities of these units. Our language model proves surprisingly good at identifying the selectional restrictions of English derivational morphemes, a task that requires both morphological and syntactic awareness. Thus we conclude that, when morphemes overlap extensively with the words of a language, a character language model can perform morphological abstraction."
}