编辑推荐 Statistical machine translation (SMT) offers many benefits over rule based and example based machine translation especially ease to train and robustness. It represents state-of-the-art in machine translation (MT) but it has to deal with certain issues that are not trivial to solve in a statistical framework: correct distortion, correct agreement, morphology issues, etc. In order to solve distortion issues, different models were proposed: syntax-based MT, enhanced distortion models, clause restructuring. All of these define more complex distortion models than monotonic distortion models (which favor lack of word reordering). These proposed models don't completely solve the issue of easily adding linguistic knowledge into the MT decoder. The work proposes a model designed to augment SMT models with linguistic knowledge, either in a rule-based fashion or in a probabilistic fashion. The theoretical framework proposed in this work was implemented in Phramer statistical phrase-based decoder and tested using various levels of knowledge - surface, part of speech, constituency parse trees. The experimental results show improvement in the quality of the translation.
