Daiber, J., Stanojević, M., Aziz, W. and Sima'an, K. (2016) Examining the Relationship between Preordering and Word Order Freedom in Machine Translation. In Proceedings of the First Conference on Machine Translation.
An implementation of mophology induction using word embeddings (Soricut, Radu, and Franz Och. "Unsupervised morphology induction using word embeddings." Proc. NAACL. 2015.)
https://github.com/jodaiber/vec2morph
Daiber, J. and Sima’an, K (2015). Delimiting Morphosyntactic Search Space with Source-Side Reordering Models. In Proceedings of the first Deep Machine Translation Workshop. Prague, Czech Republic.
Daiber, J. and Sima’an, K (2015). Machine Translation with Source-Predicted Target Morphology. Proceedings of MT Summit XV. Miami, USA.
A high-quality compound splitter based on the semantic regularities in the vector space of word embeddings. Initially, we provide models for German, but broader language support will be added in the coming releases.
More details can be found in:
Joachim Daiber, Lautaro Quiroz, Roger Wechsler and Stella Frank (2015) Splitting Compounds by Semantic Analogy. In Proceedings of the 1st Deep Machine Translation Workshop, Prague, Czech Republic, pp. 20 - 28
