@inproceedings{johny-etal-2021-finite,
    title = "Finite-state script normalization and processing utilities: The {N}isaba {B}rahmic library",
    author = "Johny, Cibu  and
      Wolf-Sonkin, Lawrence  and
      Gutkin, Alexander  and
      Roark, Brian",
    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
    month = apr,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.eacl-demos.3",
    doi = "10.18653/v1/2021.eacl-demos.3",
    pages = "14--23",
    abstract = "This paper presents an open-source library for efficient low-level processing of ten major South Asian Brahmic scripts. The library provides a flexible and extensible framework for supporting crucial operations on Brahmic scripts, such as NFC, visual normalization, reversible transliteration, and validity checks, implemented in Python within a finite-state transducer formalism. We survey some common Brahmic script issues that may adversely affect the performance of downstream NLP tasks, and provide the rationale for finite-state design and system implementation details.",
}