In this paper we study in detail the relation between word alignment and phrase extraction. First, we analyze different word alignments according to several characteristics and compare 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.

@inproceedings{guzman:2009:reassessment, Author = {Guzm{\'a}n, Francisco and Gao, Qin and Vogel, Stephan}, Booktitle = {The Twelfth Machine Translation Summit ({MTSummit XII})}, Organization = {International Association for Machine Translation}, Title = {Reassessment of the Role of Phrase Extraction in {PBSMT} }, address = {Ottawa, Canada}, Month = {August}, Year = {2009}, Abstract ={In this paper we study in detail the relation between word alignment and phrase extraction. First, we analyze different word alignments according to several characteristics and compare 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.}}