@inproceedings{schaefer-etal-2022-selecting,
    title = "On Selecting Training Corpora for Cross-Domain Claim Detection",
    author = "Schaefer, Robin  and
      Knaebel, Ren{\'e}  and
      Stede, Manfred",
    editor = "Lapesa, Gabriella  and
      Schneider, Jodi  and
      Jo, Yohan  and
      Saha, Sougata",
    booktitle = "Proceedings of the 9th Workshop on Argument Mining",
    month = oct,
    year = "2022",
    address = "Online and in Gyeongju, Republic of Korea",
    publisher = "International Conference on Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.argmining-1.17/",
    pages = "181--186",
    abstract = "Identifying claims in text is a crucial first step in argument mining. In this paper, we investigate factors for the composition of training corpora to improve cross-domain claim detection. To this end, we use four recent argumentation corpora annotated with claims and submit them to several experimental scenarios. Our results indicate that the {\textquotedblleft}ideal{\textquotedblright} composition of training corpora is characterized by a large corpus size, homogeneous claim proportions, and less formal text domains."
}