@inproceedings{moran-lignos-2020-effective,
    title = "Effective Architectures for Low Resource Multilingual Named Entity Transliteration",
    author = "Moran, Molly  and
      Lignos, Constantine",
    editor = "Karakanta, Alina  and
      Ojha, Atul Kr.  and
      Liu, Chao-Hong  and
      Abbott, Jade  and
      Ortega, John  and
      Washington, Jonathan  and
      Oco, Nathaniel  and
      Lakew, Surafel Melaku  and
      Pirinen, Tommi A  and
      Malykh, Valentin  and
      Logacheva, Varvara  and
      Zhao, Xiaobing",
    booktitle = "Proceedings of the 3rd Workshop on Technologies for MT of Low Resource Languages",
    month = dec,
    year = "2020",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.loresmt-1.11/",
    doi = "10.18653/v1/2020.loresmt-1.11",
    pages = "79--86",
    abstract = "In this paper, we evaluate LSTM, biLSTM, GRU, and Transformer architectures for the task of name transliteration in a many-to-one multilingual paradigm, transliterating from 590 languages to English. We experiment with different encoder-decoder combinations and evaluate them using accuracy, character error rate, and an F-measure based on longest continuous subsequences. We find that using a Transformer for the encoder and decoder performs best, improving accuracy by over 4 points compared to previous work. We explore whether manipulating the source text by adding macrolanguage flag tokens or pre-romanizing source strings can improve performance and find that neither manipulation has a positive effect. Finally, we analyze performance differences between the LSTM and Transformer encoders when using a Transformer decoder and find that the Transformer encoder is better able to handle insertions and substitutions when transliterating."
}