@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",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://preview.aclanthology.org/add-emnlp-2024-awards/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."
}
Markdown (Informal)
[NerKor+Cars-OntoNotes++](https://preview.aclanthology.org/add-emnlp-2024-awards/2022.lrec-1.203/) (Novák & Novák, LREC 2022)
ACL
- Attila Novák and Borbála Novák. 2022. NerKor+Cars-OntoNotes++. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1907–1916, Marseille, France. European Language Resources Association.