匈牙利命名实体识别模型与OntoNotes5 +更多实体类型

• 使用的预训练模型：SZTAKI-HLT/hubert-base-cc
• 在NerKor+CARS-ONPP语料库上进行微调

限制

• 最大序列长度 = 448

训练数据

底层语料库, NerKor+CARS-OntoNotes++ ,是从 NYTK-NerKor 派生而来的，后者是一个匈牙利黄金标准的命名实体标注语料库，包含约1百万个标记。它还包括了来自 hvg.hu 新闻档案馆的大约12k个关于机动车辆（汽车，公共汽车，摩托车）的文本标记。尽管在NYTK-NerKor的标注中遵循了CoNLL2002的标注规范，只有四个命名实体类别（ PER ， LOC ， MISC ， ORG ），但这个版本的语料库包含了30多种实体类型，包括所有在[OntoNotes 5.0]英文命名实体标注中使用的实体类型。新的标注详细说明了 LOC 和 MISC 实体类型的子类型，并包括了对时间和日期、数量、语言、国籍或宗教或政治团体等非命名实体的标注。这份注解还详细介绍了在 Ontonotes 5 注解中不存在的其他实体子类型（见下文）。

从OntoNotes 5.0注释中导出的标签

根据以下一组类型进行注释：

下列内容也以类似名称的方式进行了注释：

其他标签（不在OntoNotes 5中）

类型为 MISC 的进一步子类型的名称：

进一步的非命名实体：

如果您使用了该模型，请引用：

@inproceedings{novak-novak-2022-nerkor,
    title = "{N}er{K}or+{C}ars-{O}nto{N}otes++",
    author = "Nov{\'a}k, Attila  and
      Nov{\'a}k, Borb{\'a}la",
    booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
    month = jun,
    year = "2022",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://aclanthology.org/2022.lrec-1.203",
    pages = "1907--1916",
    abstract = "In this paper, we present an upgraded version of the Hungarian NYTK-NerKor named entity corpus, which contains about twice as many annotated spans and 7 times as many distinct entity types as the original version. We used an extended version of the OntoNotes 5 annotation scheme including time and numerical expressions. NerKor is the newest and biggest NER corpus for Hungarian containing diverse domains. We applied cross-lingual transfer of NER models trained for other languages based on multilingual contextual language models to preannotate the corpus. We corrected the annotation semi-automatically and manually. Zero-shot preannotation was very effective with about 0.82 F1 score for the best model. We also added a 12000-token subcorpus on cars and other motor vehicles. We trained and release a transformer-based NER tagger for Hungarian using the annotation in the new corpus version, which provides similar performance to an identical model trained on the original version of the corpus.",
}