@inproceedings{manukonda-kodali-2025-bytesizedllm,
    title = "byte{S}ized{LLM}@{NLU} of {D}evanagari Script Languages 2025: Language Identification Using Customized Attention {B}i{LSTM} and {XLM}-{R}o{BERT}a base Embeddings",
    author = "Manukonda, Durga Prasad  and
      Kodali, Rohith Gowtham",
    editor = "Sarveswaran, Kengatharaiyer  and
      Vaidya, Ashwini  and
      Krishna Bal, Bal  and
      Shams, Sana  and
      Thapa, Surendrabikram",
    booktitle = "Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2025.chipsal-1.26/",
    pages = "248--252",
    abstract = "This study explores the challenges of natural language understanding (NLU) in multilingual contexts, focusing on Devanagari-scripted languages such as Nepali, Marathi, Sanskrit, Bhojpuri, and Hindi. Language identification within these languages is complex due to their structural and lexical similarities. We present a hybrid Attention BiLSTM-XLM-RoBERTa model, achieving a state-of-the-art F1 score of 0.9974 on the test set, despite limited resources. Our model effectively distinguishes between closely related Devanagari-scripted languages, providing a solid foundation for context-aware NLU systems that enhance language-specific processing and promote inclusive digital interactions across diverse linguistic communities."
}