@inproceedings{ruiz-federico-2012-mdi,
    title = "{MDI} adaptation for the lazy: avoiding normalization in {LM} adaptation for lecture translation",
    author = "Ruiz, Nick  and
      Federico, Marcello",
    booktitle = "Proceedings of the 9th International Workshop on Spoken Language Translation: Papers",
    month = dec # " 6-7",
    year = "2012",
    address = "Hong Kong, Table of contents",
    url = "https://preview.aclanthology.org/fix-sig-urls/2012.iwslt-papers.14/",
    pages = "244--251",
    abstract = "This paper provides a fast alternative to Minimum Discrimination Information-based language model adaptation for statistical machine translation. We provide an alternative to computing a normalization term that requires computing full model probabilities (including back-off probabilities) for all n-grams. Rather than re-estimating an entire language model, our Lazy MDI approach leverages a smoothed unigram ratio between an adaptation text and the background language model to scale only the n-gram probabilities corresponding to translation options gathered by the SMT decoder. The effects of the unigram ratio are scaled by adding an additional feature weight to the log-linear discriminative model. We present results on the IWSLT 2012 TED talk translation task and show that Lazy MDI provides comparable language model adaptation performance to classic MDI."
}