We here describe the subword approach we used in the 2006 ImageCLEF Medical Image Retrieval task. It is based on the assupmtion that neither fully inflected nor automatically stem...
We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...
—We describe the design of an autonomous agent that can teach itself how to translate from a foreign language, by first assembling its own training set, then using it to improve...
Multilingual parallel text corpora provide a powerful means for propagating linguistic knowledge across languages. We present a model which jointly learns linguistic structure for...
Biomedical images and captions are one of the major sources of information in online biomedical publications. They often contain the most important results to be reported, and pro...
Xin Chen, Caimei Lu, Yuan An, Palakorn Achananupar...