Enhancing Low Resource NER Using Assisting Language And Transfer Learning
This work addresses NER for low-resource Indian languages, which is incremental as it applies existing BERT methods to new language pairs with minor adaptations.
The paper tackled Named Entity Recognition (NER) for low-resource Indian languages like Hindi and Marathi by using adaptations of BERT models and transfer learning, showing that multilingual training improves performance over monolingual approaches, though data selection is needed to avoid issues from blind dataset mixing.
Named Entity Recognition (NER) is a fundamental task in NLP that is used to locate the key information in text and is primarily applied in conversational and search systems. In commercial applications, NER or comparable slot-filling methods have been widely deployed for popular languages. NER is used in applications such as human resources, customer service, search engines, content classification, and academia. In this paper, we draw focus on identifying name entities for low-resource Indian languages that are closely related, like Hindi and Marathi. We use various adaptations of BERT such as baseBERT, AlBERT, and RoBERTa to train a supervised NER model. We also compare multilingual models with monolingual models and establish a baseline. In this work, we show the assisting capabilities of the Hindi and Marathi languages for the NER task. We show that models trained using multiple languages perform better than a single language. However, we also observe that blind mixing of all datasets doesn't necessarily provide improvements and data selection methods may be required.