@inproceedings{doostmohammadi-etal-2020-joint,
    title = "Joint {P}ersian Word Segmentation Correction and Zero-Width Non-Joiner Recognition Using {BERT}",
    author = "Doostmohammadi, Ehsan  and
      Nassajian, Minoo  and
      Rahimi, Adel",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2020.coling-main.406/",
    doi = "10.18653/v1/2020.coling-main.406",
    pages = "4612--4618",
    abstract = "Words are properly segmented in the Persian writing system; in practice, however, these writing rules are often neglected, resulting in single words being written disjointedly and multiple words written without any white spaces between them. This paper addresses the problems of word segmentation and zero-width non-joiner (ZWNJ) recognition in Persian, which we approach jointly as a sequence labeling problem. We achieved a macro-averaged F1-score of 92.40{\%} on a carefully collected corpus of 500 sentences with a high level of difficulty."
}