@inproceedings{zhang-zweigenbaum-2017-znlp,
    title = "z{NLP}: Identifying Parallel Sentences in {C}hinese-{E}nglish Comparable Corpora",
    author = "Zhang, Zheng  and
      Zweigenbaum, Pierre",
    editor = "Sharoff, Serge  and
      Zweigenbaum, Pierre  and
      Rapp, Reinhard",
    booktitle = "Proceedings of the 10th Workshop on Building and Using Comparable Corpora",
    month = aug,
    year = "2017",
    address = "Vancouver, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/W17-2510/",
    doi = "10.18653/v1/W17-2510",
    pages = "51--55",
    abstract = "This paper describes the zNLP system for the BUCC 2017 shared task. Our system identifies parallel sentence pairs in Chinese-English comparable corpora by translating word-by-word Chinese sentences into English, using the search engine Solr to select near-parallel sentences and then by using an SVM classifier to identify true parallel sentences from the previous results. It obtains an F1-score of 45{\%} (resp. 32{\%}) on the test (training) set."
}