Beheshti-NER: Persian Named Entity Recognition Using BERT

TL;DR

This paper presents a Persian Named Entity Recognition model based on BERT, achieving competitive results and second place in a related NLP competition.

Contribution

It adapts BERT for Persian NER and compares its performance with previous state-of-the-art models, demonstrating improved results.

Findings

Achieved 83.5 F1 score at phrase level

Achieved 88.4 F1 score at word level

Secured second place in NSURL-2019 NER competition

Abstract

Named entity recognition is a natural language processing task to recognize and extract spans of text associated with named entities and classify them in semantic Categories. Google BERT is a deep bidirectional language model, pre-trained on large corpora that can be fine-tuned to solve many NLP tasks such as question answering, named entity recognition, part of speech tagging and etc. In this paper, we use the pre-trained deep bidirectional network, BERT, to make a model for named entity recognition in Persian. We also compare the results of our model with the previous state of the art results achieved on Persian NER. Our evaluation metric is CONLL 2003 score in two levels of word and phrase. This model achieved second place in NSURL-2019 task 7 competition which associated with NER for the Persian language. our results in this competition are 83.5 and 88.4 f1 CONLL score respectively in phrase and word level evaluation.