Reordering via N-best lists for Spanish-Basque translation

In Statistical Machine Translation (SMT), one of the main problems they are confronted with is the problem stemming from the differ-ent word order that different lan-guages imply. Most works address-ing this issue centre their effort in pairs of languages involving Ara-bic, Japanese or Chinese because of their utmost different origin with re-spect to western languages. How-ever, Basque is also a language with an extremely different word order with respect to most other Euro-pean languages, linguists being un-able to determine its origins with certainty. Hence, SMT systems which do not tackle the reordering problem in any way are mostly un-able to yield satisfactory results. In this work, a novel source sentence reordering technique is presented, based on monotonized alignments and n-best lists, endorsed by very promissing results obtained from a Basque-Spanish translation task.