Deep Learning Transformer Architecture for Named Entity Recognition on Low Resourced Languages: State of the art results
It addresses the problem of limited NER capabilities for low-resourced languages, enabling high-performance NLP with reduced effort and costs, though it is incremental as it applies existing transformer methods to new data.
This paper tackled Named Entity Recognition (NER) on ten low-resourced South African languages using transformer models, achieving state-of-the-art results with the highest F-scores for six languages and the highest average F-score, surpassing other models like Conditional Random Fields.
This paper reports on the evaluation of Deep Learning (DL) transformer architecture models for Named-Entity Recognition (NER) on ten low-resourced South African (SA) languages. In addition, these DL transformer models were compared to other Neural Network and Machine Learning (ML) NER models. The findings show that transformer models substantially improve performance when applying discrete fine-tuning parameters per language. Furthermore, fine-tuned transformer models outperform other neural network and machine learning models on NER with the low-resourced SA languages. For example, the transformer models obtained the highest F-scores for six of the ten SA languages and the highest average F-score surpassing the Conditional Random Fields ML model. Practical implications include developing high-performance NER capability with less effort and resource costs, potentially improving downstream NLP tasks such as Machine Translation (MT). Therefore, the application of DL transformer architecture models for NLP NER sequence tagging tasks on low-resourced SA languages is viable. Additional research could evaluate the more recent transformer architecture models on other Natural Language Processing tasks and applications, such as Phrase chunking, MT, and Part-of-Speech tagging.