@article{liu-prudhommeaux-2023-data,
    title = "Data-driven Parsing Evaluation for Child-Parent Interactions",
    author = "Liu, Zoey  and
      Prud{'}hommeaux, Emily",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "11",
    year = "2023",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.tacl-1.97/",
    doi = "10.1162/tacl_a_00624",
    pages = "1734--1753",
    abstract = "We present a syntactic dependency treebank for naturalistic child and child-directed spoken English. Our annotations largely follow the guidelines of the Universal Dependencies project (UD [Zeman et al., 2022]), with detailed extensions to lexical and syntactic structures unique to spontaneous spoken language, as opposed to written texts or prepared speech. Compared to existing UD-style spoken treebanks and other dependency corpora of child-parent interactions specifically, our dataset is much larger (44,744 utterances; 233,907 words) and contains data from 10 children covering a wide age range (18{--}66 months). We conduct thorough dependency parser evaluations using both graph-based and transition-based parsers, trained on three different types of out-of-domain written texts: news, tweets, and learner data. Out-of-domain parsers demonstrate reasonable performance for both child and parent data. In addition, parser performance for child data increases along children{'}s developmental paths, especially between 18 and 48 months, and gradually approaches the performance for parent data. These results are further validated with in-domain training."
}