عکس AminMozhgani
Persian Name Entity Recognition tool based on ArmanPersoNERCorpusPython
موضوع‌ها
۰
فورک‌ها
۴
ستاره‌ها
۱۷
تاریخ ایجاد
۲۲ دی ۱۳۹۶
آخرین بروزرسانی
بیشتر از ۴ سال قبل
لایسنس
GNU General Public License v3.0

Persian_NER

Persian Name Entity Recognition tool based on ArmanPersoNERCorpus

مهدی : B-pers
طارمی : I-pers
با : O
تیم : B-org
الغرافه : I-org
قطر : I-org
به : O
توافق : O
رسید : O
. : O

Training

Based on ArmanPersoNERCorpus , I've trained a model and it's ready to use. The training tool is developed by Python and using Tensorflow. I've customized guillaumegenthial source codes for this purpose.

Using

First of all, you should download this file and extract it to the main folder. It will create a folder named results . You can find a file in data folder called input.txt . Put your text there and call Python evaluate.py . Your desired results will be written in data/result.txt .

If you want to train your own model, follow instructions in https://github.com/guillaumegenthial/sequence_tagging.

Citations

Hanieh Poostchi, Ehsan Zare Borzeshi, Mohammad Abdous, and Massimo Piccardi, "PersoNER: Persian Named-Entity Recognition," The 26th International Conference on Computational Linguistics (COLING 2016), pages 3381–3389, Osaka, Japan, 2016.

Hanieh Poostchi, Ehsan Zare Borzeshi, and Massimo Piccardi, "BiLSTM-CRF for Persian Named-Entity Recognition; ArmanPersoNERCorpus: the First Entity-Annotated Persian Dataset," The 11th Edition of the Language Resources and Evaluation Conference (LREC), Miyazaki, Japan, 7-12 May 2018, ISLRN 399-379-640-828-6, ISLRN 921-509-141-609-6.