AsNER -- Annotated Dataset and Baseline for Assamese Named Entity recognition
This provides a valuable resource for low-resource Assamese language processing, though it is incremental as it applies existing methods to new data.
The authors tackled the lack of resources for Assamese named entity recognition by creating AsNER, a dataset with about 99k tokens from speeches and plays, and developed a baseline model that achieved an F1-score of 80.69% using MuRIL embeddings.
We present the AsNER, a named entity annotation dataset for low resource Assamese language with a baseline Assamese NER model. The dataset contains about 99k tokens comprised of text from the speech of the Prime Minister of India and Assamese play. It also contains person names, location names and addresses. The proposed NER dataset is likely to be a significant resource for deep neural based Assamese language processing. We benchmark the dataset by training NER models and evaluating using state-of-the-art architectures for supervised named entity recognition (NER) such as Fasttext, BERT, XLM-R, FLAIR, MuRIL etc. We implement several baseline approaches with state-of-the-art sequence tagging Bi-LSTM-CRF architecture. The highest F1-score among all baselines achieves an accuracy of 80.69% when using MuRIL as a word embedding method. The annotated dataset and the top performing model are made publicly available.