L3Cube-MahaNER: A Marathi Named Entity Recognition Dataset and BERT models

Anonymous

Keywords: Named Entity Recognition, Dataset, Transformers, Natural Language Processing

TL;DR: We present L3Cube-MahaNER, the first major gold standard named entity recognition dataset in Marathi. We also present benchmark results on BERT, CNN and LSTM based models.

Abstract: Named Entity Recognition (NER) is a basic NLP task and finds major applications in conversational and search systems. It helps us identify key entities in a sentence useful for the downstream application. NER or similar slot filling systems for popular languages have been heavily used in commercial applications. In this work, we focus on Marathi, an Indian language, spoken prominently by the people of Maharashtra state. Marathi is a low resource language and still lacks useful NER resources. We present L3Cube-MahaNER, the first major gold standard named entity recognition dataset in Marathi. We also describe the manual annotation guidelines followed during the process. In the end, we also benchmark the dataset on different CNN, LSTM, and Transformer based models.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2204.06029/code)