Mono vs Multilingual BERT: A Case Study in Hindi and Marathi Named Entity Recognition
This work addresses NER for low-resource Indian languages, providing missing baselines, but is incremental as it applies existing methods to new data.
The study benchmarked monolingual and multilingual BERT variants for named entity recognition in Hindi and Marathi, finding that MahaRoBERTa performed best for Marathi and XLM-RoBERTa for Hindi, with cross-language evaluation yielding mixed results.
Named entity recognition (NER) is the process of recognising and classifying important information (entities) in text. Proper nouns, such as a person's name, an organization's name, or a location's name, are examples of entities. The NER is one of the important modules in applications like human resources, customer support, search engines, content classification, and academia. In this work, we consider NER for low-resource Indian languages like Hindi and Marathi. The transformer-based models have been widely used for NER tasks. We consider different variations of BERT like base-BERT, RoBERTa, and AlBERT and benchmark them on publicly available Hindi and Marathi NER datasets. We provide an exhaustive comparison of different monolingual and multilingual transformer-based models and establish simple baselines currently missing in the literature. We show that the monolingual MahaRoBERTa model performs the best for Marathi NER whereas the multilingual XLM-RoBERTa performs the best for Hindi NER. We also perform cross-language evaluation and present mixed observations.