@inproceedings{sokolov-etal-2012-non,
    title = "Non-linear n-best List Reranking with Few Features",
    author = "Sokolov, Artem  and
      Wisniewski, Guillaume  and
      Yvon, Fran{\c{c}}ois",
    booktitle = "Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers",
    month = oct # " 28-" # nov # " 1",
    year = "2012",
    address = "San Diego, California, USA",
    publisher = "Association for Machine Translation in the Americas",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2012.amta-papers.17/",
    abstract = "In Machine Translation, it is customary to compute the model score of a predicted hypothesis as a linear combination of multiple features, where each feature assesses a particular facet of the hypothesis. The choice of a linear combination is usually justified by the possibility of efficient inference (decoding); yet, the appropriateness of this simple combination scheme to the task at hand is rarely questioned. In this paper, we propose an approach that replaces the linear scoring function with a non-linear scoring function. To investigate the applicability of this approach, we rescore n-best lists generated with a conventional machine translation engine (using a linear scoring function for generating its hypotheses) with a non-linear scoring function learned using the learning-to-rank framework. Moderate, though consistent, gains in BLEU are demonstrated on the WMT`10, WMT`11 and WMT`12 test sets."
}