@inproceedings{li-khudanpur-2008-large,
    title = "Large-scale Discriminative n-gram Language Models for Statistical Machine Translation",
    author = "Li, Zhifei  and
      Khudanpur, Sanjeev",
    booktitle = "Proceedings of the 8th Conference of the Association for Machine Translation in the Americas: Research Papers",
    month = oct # " 21-25",
    year = "2008",
    address = "Waikiki, USA",
    publisher = "Association for Machine Translation in the Americas",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2008.amta-papers.12/",
    pages = "133--142",
    abstract = "We extend discriminative n-gram language modeling techniques originally proposed for automatic speech recognition to a statistical machine translation task. In this context, we propose a novel data selection method that leads to good models using a fraction of the training data. We carry out systematic experiments on several benchmark tests for Chinese to English translation using a hierarchical phrase-based machine translation system, and show that a discriminative language model significantly improves upon a state-of-the-art baseline. The experiments also highlight the benefits of our data selection method."
}