@inproceedings{striebel-etal-2024-domain,
    title = "Domain-Weighted Batch Sampling for Neural Dependency Parsing",
    author = {Striebel, Jacob  and
      Dakota, Daniel  and
      K{\"u}bler, Sandra},
    editor = {Bhatia, Archna  and
      Bouma, Gosse  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Evang, Kilian  and
      Garcia, Marcos  and
      Giouli, Voula  and
      Han, Lifeng  and
      Nivre, Joakim  and
      Rademaker, Alexandre},
    booktitle = "Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.mwe-1.24/",
    pages = "198--206",
    abstract = "In neural dependency parsing, as well as in the broader field of NLP, domain adaptation remains a challenging problem. When adapting a parser to a target domain, there is a fundamental tension between the need to make use of out-of-domain data and the need to ensure that syntactic characteristic of the target domain are learned. In this work we explore a way to balance these two competing concerns, namely using domain-weighted batch sampling, which allows us to use all available training data, while controlling the probability of sampling in- and out-of-domain data when constructing training batches. We conduct experiments using ten natural language domains and find that domain-weighted batch sampling yields substantial performance improvements in all ten domains compared to a baseline of conventional randomized batch sampling."
}