@inproceedings{hearne-etal-2008-comparing,
    title = "Comparing Constituency and Dependency Representations for {SMT} Phrase-Extraction",
    author = "Hearne, Mary  and
      Ozdowska, Sylwia  and
      Tinsley, John",
    editor = "B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Bonastre, Jean-Francois",
    booktitle = "Actes de la 15{\`e}me conf{\'e}rence sur le Traitement Automatique des Langues Naturelles. Articles courts",
    month = jun,
    year = "2008",
    address = "Avignon, France",
    publisher = "ATALA",
    url = "https://preview.aclanthology.org/fix-sig-urls/2008.jeptalnrecital-court.14/",
    pages = "131--140",
    abstract = "We consider the value of replacing and/or combining string-basedmethods with syntax-based methods for phrase-based statistical machine translation (PBSMT), and we also consider the relative merits of using constituency-annotated vs. dependency-annotated training data. We automatically derive two subtree-aligned treebanks, dependency-based and constituency-based, from a parallel English{--}French corpus and extract syntactically motivated word- and phrase-pairs. We automatically measure PB-SMT quality. The results show that combining string-based and syntax-based word- and phrase-pairs can improve translation quality irrespective of the type of syntactic annotation. Furthermore, using dependency annotation yields greater translation quality than constituency annotation for PB-SMT."
}