@InProceedings{beloucif-saers-wu:2016:HyTra6,
  author    = {Beloucif, Meriem  and  Saers, Markus  and  Wu, Dekai},
  title     = {Improving word alignment for low resource languages using English monolingual SRL},
  booktitle = {Proceedings of the Sixth Workshop on Hybrid Approaches to Translation (HyTra6)},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {51--60},
  abstract  = {We introduce a new statistical machine translation approach specifically geared
	to learning translation from low resource languages, that exploits monolingual
	English semantic parsing to bias inversion transduction grammar (ITG)
	induction. We show that in contrast to conventional statistical machine
	translation (SMT) training methods, which rely heavily on phrase memorization,
	our approach focuses on learning bilingual correlations that help translating
	low resource languages, by using the output language semantic structure to
	further narrow down ITG constraints. This approach is motivated by previous
	research which has shown that injecting a semantic frame based objective
	function while training SMT models improves the translation quality. We show
	that including a monolingual semantic objective function during the learning of
	the translation model leads towards a semantically driven alignment which is
	more efficient than simply tuning loglinear mixture weights against a semantic
	frame based evaluation metric in the final stage of statistical machine
	translation training. We test our approach with three different language pairs
	and demonstrate that our model biases the learning towards more semantically
	correct alignments. Both GIZA++ and ITG based techniques fail to capture
	meaningful bilingual constituents, which is required when trying to learn
	translation models for low resource languages. In contrast, our proposed model
	not only improve translation by injecting a monolingual objective function to
	learn bilingual correlations during early training of the translation model,
	but also helps to learn more meaningful correlations with a relatively small
	data set, leading to a better alignment compared to either conventional ITG or
	traditional GIZA++ based approaches.},
  url       = {http://aclweb.org/anthology/W16-4507}
}