@inproceedings{kamath-vajjala-2025-synthetic,
    title = "Does Synthetic Data Help Named Entity Recognition for Low-Resource Languages?",
    author = "Kamath, Gaurav  and
      Vajjala, Sowmya",
    editor = "Inui, Kentaro  and
      Sakti, Sakriani  and
      Wang, Haofen  and
      Wong, Derek F.  and
      Bhattacharyya, Pushpak  and
      Banerjee, Biplab  and
      Ekbal, Asif  and
      Chakraborty, Tanmoy  and
      Singh, Dhirendra Pratap",
    booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.ijcnlp-short.15/",
    pages = "159--167",
    ISBN = "979-8-89176-299-2",
    abstract = "We explore whether synthetic datasets generated by large language models using a few high quality seed samples are useful for low-resource named entity recognition, considering 11 languages from three language families. Our results suggest that synthetic data created with such seed data is a reasonable choice when there is no available labeled data, and is better than using entirely automatically labeled data. However, a small amount of high-quality data, coupled with cross-lingual transfer from a related language, always offers better performance. Data and code available at: https://github.com/grvkamath/low-resource-syn-ner."
}