@inproceedings{le-sadat-2015-building,
    title = "Building a Bilingual {V}ietnamese-{F}rench Named Entity Annotated Corpus through Cross-Linguistic Projection",
    author = "Le, Ngoc Tan  and
      Sadat, Fatiha",
    editor = "Lecarpentier, Jean-Marc  and
      Lucas, Nadine",
    booktitle = "Actes de la 22e conf{\'e}rence sur le Traitement Automatique des Langues Naturelles. D{\'e}monstrations",
    month = jun,
    year = "2015",
    address = "Caen, France",
    publisher = "ATALA",
    url = "https://preview.aclanthology.org/fix-sig-urls/2015.jeptalnrecital-demonstration.6/",
    pages = "12--13",
    abstract = "The creation of high-quality named entity annotated resources is time-consuming and an expensive process. Most of the gold standard corpora are available for English but not for less-resourced languages such as Vietnamese. In Asian languages, this task is remained problematic. This paper focuses on an automatic construction of named entity annotated corpora for Vietnamese-French, a less-resourced pair of languages. We incrementally apply different cross-projection methods using parallel corpora, such as perfect string matching and edit distance similarity. Evaluations on Vietnamese {--}French pair of languages show a good accuracy (F-score of 94.90{\%}) when identifying named entities pairs and building a named entity annotated parallel corpus."
}