@inproceedings{cathcart-rama-2020-disentangling,
    title = "Disentangling dialects: a neural approach to {I}ndo-{A}ryan historical phonology and subgrouping",
    author = "Cathcart, Chundra  and
      Rama, Taraka",
    editor = "Fern{\'a}ndez, Raquel  and
      Linzen, Tal",
    booktitle = "Proceedings of the 24th Conference on Computational Natural Language Learning",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2020.conll-1.50/",
    doi = "10.18653/v1/2020.conll-1.50",
    pages = "620--630",
    abstract = "This paper seeks to uncover patterns of sound change across Indo-Aryan languages using an LSTM encoder-decoder architecture. We augment our models with embeddings represent-ing language ID, part of speech, and other features such as word embeddings. We find that a highly augmented model shows highest accuracy in predicting held-out forms, and investigate other properties of interest learned by our models' representations. We outline extensions to this architecture that can better capture variation in Indo-Aryan sound change."
}