... combined with target language information in order to choose the besttranslation, thus improving translation quality.We position the problem of generating alterna-tive texts for translation within ... corpus.Target -language scores On the target side weused either a standard 3-gram language- model, de-noted LMT, or the score assigned by the com-plete SMT log-linear model, which includes the language ... by the applied context-models, andcan be further addressed, together with the abovementioned problems, with better source -language context models.We suggest that other types of entailment rulescould...