@inproceedings{krishnan-ragavan-2021-morphology,
    title = "Morphology-Aware Meta-Embeddings for {T}amil",
    author = "Krishnan, Arjun Sai  and
      Ragavan, Seyoon",
    editor = "Durmus, Esin  and
      Gupta, Vivek  and
      Liu, Nelson  and
      Peng, Nanyun  and
      Su, Yu",
    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2021.naacl-srw.13/",
    doi = "10.18653/v1/2021.naacl-srw.13",
    pages = "94--111",
    abstract = "In this work, we explore generating morphologically enhanced word embeddings for Tamil, a highly agglutinative South Indian language with rich morphology that remains low-resource with regards to NLP tasks. We present here the first-ever word analogy dataset for Tamil, consisting of 4499 hand-curated word tetrads across 10 semantic and 13 morphological relation types. Using a rules-based segmenter to capture morphology as well as meta-embedding techniques, we train meta-embeddings that outperform existing baselines by 16{\%} on our analogy task and appear to mitigate a previously observed trade-off between semantic and morphological accuracy."
}