Fine-tuning Pre-trained Named Entity Recognition Models For Indian Languages

TL;DR

This paper introduces a new dataset and a fine-tuned multilingual NER model for Indian languages, addressing the lack of resources and challenges in processing these languages in NLP applications.

Contribution

It provides a human-annotated corpus of 40K sentences for four Indian languages and demonstrates a fine-tuned model achieving high F1 scores, improving NER for Indian languages.

Findings

Achieved an average F1 score of 0.80 on the dataset.

Model performs well on unseen Indian language datasets.

Addresses challenges specific to Indian languages in NER.

Abstract

Named Entity Recognition (NER) is a useful component in Natural Language Processing (NLP) applications. It is used in various tasks such as Machine Translation, Summarization, Information Retrieval, and Question-Answering systems. The research on NER is centered around English and some other major languages, whereas limited attention has been given to Indian languages. We analyze the challenges and propose techniques that can be tailored for Multilingual Named Entity Recognition for Indian Languages. We present a human annotated named entity corpora of 40K sentences for 4 Indian languages from two of the major Indian language families. Additionally,we present a multilingual model fine-tuned on our dataset, which achieves an F1 score of 0.80 on our dataset on average. We achieve comparable performance on completely unseen benchmark datasets for Indian languages which affirms the usability of our model.