README.md

metadata

language:
  - grc
tags:
  - flair
  - token-classification
widget:
  - >-
    ταῦτα εἴπας ὁ Ἀλέξανδρος παρίζει Πέρσῃ ἀνδρὶ ἄνδρα Μακεδόνα ὡς γυναῖκα τῷ
    λόγῳ · οἳ δέ , ἐπείτε σφέων οἱ Πέρσαι ψαύειν ἐπειρῶντο , διεργάζοντο αὐτούς
    .

Named Entity Recognition for Ancient Greek

Pretrained NER tagging model for ancient Greek

Usage

from flair.data import Sentence
from flair.models import SequenceTagger
  
tagger = SequenceTagger.load("UGARIT/flair_grc_bert_ner")
sentence = Sentence('ταῦτα εἴπας ὁ Ἀλέξανδρος παρίζει Πέρσῃ ἀνδρὶ ἄνδρα Μακεδόνα ὡς γυναῖκα τῷ λόγῳ · οἳ δέ , ἐπείτε σφέων οἱ Πέρσαι ψαύειν ἐπειρῶντο , διεργάζοντο αὐτούς .')
tagger.predict(sentence)
for entity in sentence.get_spans('ner'):
    print(entity)

Citation

if you use this model, please consider citing this work:

@unpublished{yousetetal22
author = "Yousef, Tariq and Palladino, Chiara and Jänicke, Stefan",
title = "Transformer-Based Named Entity Recognition for Ancient Greek",
year = {2022},
month = {11},
doi = "10.13140/RG.2.2.34846.61761"
url = {https://www.researchgate.net/publication/358956953_Sequence_Labeling_Architectures_in_Diglossia_-_a_case_study_of_Arabic_and_its_dialects}
}