@inproceedings{sawaf-etal-2000-use,
    title = "On the Use of Grammar Based Language Models for Statistical Machine Translation",
    author = {Sawaf, Hassan  and
      Sch{\"u}tz, Kai  and
      Ney, Hermann},
    editor = "Lavelli, Alberto  and
      Carroll, John  and
      Berwick, Robert C.  and
      Bunt, Harry C.  and
      Carpenter, Bob  and
      Carroll, John  and
      Church, Ken  and
      Johnson, Mark  and
      Joshi, Aravind  and
      Kaplan, Ronald  and
      Kay, Martin  and
      Lang, Bernard  and
      Lavie, Alon  and
      Nijholt, Anton  and
      Samuelsson, Christer  and
      Steedman, Mark  and
      Stock, Oliviero  and
      Tanaka, Hozumi  and
      Tomita, Masaru  and
      Uszkoreit, Hans  and
      Vijay-Shanker, K.  and
      Weir, David  and
      Wiren, Mats",
    booktitle = "Proceedings of the Sixth International Workshop on Parsing Technologies",
    month = feb # " 23-25",
    year = "2000",
    address = "Trento, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2000.iwpt-1.23/",
    pages = "231--241",
    abstract = "In this paper, we describe some concepts of language models beyond the usually used standard trigram and use such language models for statistical machine translation. In statistical machine translation the language model is the a-priori knowledge source of the system about the target language. One important requirement for the language model is the correct word order, given a certain choice of words, and to score the translations generated by the translation model $\textrm{Pr}(f_1^J/e^I_1)$, in view of the syntactic context. In addition to standard $m$-grams with long histories, we examine the use of Part-of-Speech based models as well as linguistically motivated grammars with stochastic parsing as a special type of language model. Translation results are given on the VERBMOBIL task, where translation is performed from German to English, with vocabulary sizes of 6500 and 4000 words, respectively."
}