Views
No views yet
1from transformers import BertTokenizer, BertForTokenClassification
2from transformers import pipeline
3
4tokenizer = BertTokenizer.from_pretrained('tartuNLP/EstBERT_NER')
5bertner = BertForTokenClassification.from_pretrained('tartuNLP/EstBERT_NER')
6
7nlp = pipeline("ner", model=bertner, tokenizer=tokenizer)
8sentence = 'Eesti Ekspressi teada on Eesti Pank uurinud Hansapanga tehinguid , mis toimusid kaks aastat tagasi suvel ja mille käigus voolas panka ligi miljardi krooni ulatuses kahtlast raha .'
9
10ner_results = nlp(sentence)
11print(ner_results)[{'word': 'Eesti', 'score': 0.9964128136634827, 'entity': 'B-ORG', 'index': 1}, {'word': 'Ekspressi', 'score': 0.9978809356689453, 'entity': 'I-ORG', 'index': 2}, {'word': 'Eesti', 'score': 0.9988121390342712, 'entity': 'B-ORG', 'index': 5}, {'word': 'Pank', 'score': 0.9985784292221069, 'entity': 'I-ORG', 'index': 6}, {'word': 'Hansapanga', 'score': 0.9979034662246704, 'entity': 'B-ORG', 'index': 8}]
@inproceedings{tanvir-etal-2021-estbert,
title = {{EstBERT: A Pretrained Language-Specific BERT for Estonian}},
author = "Tanvir, Hasan and
Kittask, Claudia and
Eiche, Sandra and
Sirts, Kairit",
editor = "Dobnik, Simon and
{\O}vrelid, Lilja",
booktitle = "Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)",
year = "2021",
address = "Reykjavik, Iceland (Online)",
publisher = {Link{\"o}ping University Electronic Press, Sweden},
url = "https://aclanthology.org/2021.nodalida-main.2/",
pages = "11--19"
}@misc{tanvir2020estbert,
title={EstBERT: A Pretrained Language-Specific BERT for Estonian},
author={Hasan Tanvir and Claudia Kittask and Kairit Sirts},
year={2020},
eprint={2011.04784},
archivePrefix={arXiv},
primaryClass={cs.CL}
}