@inproceedings{weber-steedman-2021-fine,
    title = "Fine-grained General Entity Typing in {G}erman using {G}erma{N}et",
    author = "Weber, Sabine  and
      Steedman, Mark",
    editor = "Panchenko, Alexander  and
      Malliaros, Fragkiskos D.  and
      Logacheva, Varvara  and
      Jana, Abhik  and
      Ustalov, Dmitry  and
      Jansen, Peter",
    booktitle = "Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2021.textgraphs-1.14/",
    doi = "10.18653/v1/2021.textgraphs-1.14",
    pages = "138--143",
    abstract = "Fine-grained entity typing is important to tasks like relation extraction and knowledge base construction. We find however, that fine-grained entity typing systems perform poorly on general entities (e.g. {\textquotedblleft}ex-president{\textquotedblright}) as compared to named entities (e.g. {\textquotedblleft}Barack Obama{\textquotedblright}). This is due to a lack of general entities in existing training data sets. We show that this problem can be mitigated by automatically generating training data from WordNets. We use a German WordNet equivalent, GermaNet, to automatically generate training data for German general entity typing. We use this data to supplement named entity data to train a neural fine-grained entity typing system. This leads to a 10{\%} improvement in accuracy of the prediction of level 1 FIGER types for German general entities, while decreasing named entity type prediction accuracy by only 1{\%}."
}