Reassessment of the Role of Phrase Extraction in PBSMT
Francisco Guzmán, Qin Xiang Gao, Stephan Vogel · 2009
In this paper we study in detail the relation be-tween word alignment and phrase extraction. First, we analyze different word alignments according to several characteristics and com-pare them to hand-aligned data. Secondly, we analyzed the phrase-pairs generated by these alignments. We observed that the number of unaligned words has a large impact on the characteristics of the phrase table. A manual evaluation of phrase pair quality showed that the increase in the number of unaligned words results in a lower quality. Finally, we present translation results from using the number of unaligned words as features from which we obtain up to 2BP of improvement. 1