@inproceedings{agarwal-nenkova-2023-named,
    title = "Named Entity Recognition in a Very Homogenous Domain",
    author = "Agarwal, Oshin  and
      Nenkova, Ani",
    editor = "Vlachos, Andreas  and
      Augenstein, Isabelle",
    booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
    month = may,
    year = "2023",
    address = "Dubrovnik, Croatia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2023.findings-eacl.138/",
    doi = "10.18653/v1/2023.findings-eacl.138",
    pages = "1850--1855",
    abstract = "Machine Learning models have lower accuracy when tested on out-of-domain data. Developing models that perform well on several domains or can be quickly adapted to a new domain is an important research area. Domain, however, is a vague term, that can refer to any aspect of data such as language, genre, source and structure. We consider a very homogeneous source of data, specifically sentences from news articles from the same newspaper in English, and collect a dataset of such {\textquotedblleft}in-domain{\textquotedblright} sentences annotated with named entities. We find that even in such a homogeneous domain, the performance of named entity recognition models varies significantly across news topics. Selection of diverse data, as we demonstrate, is crucial even in a seemingly homogeneous domain."
}