@inproceedings{bojar-prokopova-2006-czech,
    title = "{C}zech-{E}nglish Word Alignment",
    author = "Bojar, Ond{\v{r}}ej  and
      Prokopov{\'a}, Magdelena",
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Gangemi, Aldo  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Odijk, Jan  and
      Tapias, Daniel",
    booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
    month = may,
    year = "2006",
    address = "Genoa, Italy",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/fix-sig-urls/L06-1158/",
    abstract = "We describe an experiment with Czech-English word alignment. Half a thousand sentences were manually annotated by two annotators in parallel and the most frequent reasons for disagreement are described. We evaluate the accuracy of GIZA++ alignment toolkit on the data and identify that lemmatization of the Czech part can reduce alignment error to a half. Furthermore we document that about 38{\%} of tokens difficult for GIZA++ were difficult for humans already."
}