Tuning syntactically enhanced word alignment for statistical machine translation
Ma, Yanjun and Lambert, Patrik and Way, Andy (2009) Tuning syntactically enhanced word alignment for statistical machine translation. In: EAMT 2009 - 13th Annual Conference of the European Association for Machine Translation, 13-15 May 2009, Barcelona, Spain.
Full text available as:
We introduce a syntactically enhanced word alignment model that is more flexible than state-of-the-art generative word
alignment models and can be tuned according to different end tasks. First of all, this model takes the advantages of
both unsupervised and supervised word alignment approaches by obtaining anchor alignments from unsupervised generative
models and seeding the anchor alignments into a supervised discriminative model. Second, this model offers the flexibility of tuning the alignment according to different
optimisation criteria. Our experiments show that using our word alignment in a Phrase-Based Statistical Machine Translation system yields a 5.38% relative increase
on IWSLT 2007 task in terms of BLEU score.
Archive Staff Only: edit this record