L3Cube MahaSocialNER
L3Cube-MahaSocialNER is a large, publicly available dataset of Marathi social media text annotated for Named Entity Recognition (NER), addressing the scarcity of such resources for low-resource languages. Research focuses on evaluating various deep learning models, including CNNs, LSTMs, BiLSTMs, and Transformers, for accurate NER in this informal, code-mixed context, highlighting the challenges posed by social media language. This resource significantly contributes to the advancement of Marathi NLP and facilitates applications such as public opinion analysis and social media monitoring.
Papers
October 11, 2024
September 13, 2024
May 6, 2024
April 28, 2024
January 4, 2024
December 30, 2023
June 24, 2023
April 22, 2023
November 21, 2022
L3Cube-HindBERT and DevBERT: Pre-Trained BERT Transformer models for Devanagari based Hindi and Marathi Languages
Raviraj Joshi
L3Cube-MahaSBERT and HindSBERT: Sentence BERT Models and Benchmarking BERT Sentence Representations for Hindi and Marathi
Ananya Joshi, Aditi Kajale, Janhavi Gadre, Samruddhi Deode, Raviraj Joshi
May 29, 2022
April 18, 2022
March 25, 2022