Continuous space models of language (CSMs) are compelling for machine translation since they permit a diverse variety of contextual information to be considered when making decisions about local (e.g., lexical and morphological) and global (e.g., sentence structure and discourse) translation decisions. They thus promise to make machine translation more practical with fewer examples of parallel sentences by leveraging limited parallel data more effectively. I will present our workshop experiences and efforts in: (i) developing tools to make experimentation with continuous space translation models practical; (ii) demonstrating their effectiveness in low-resource translation scenarios; and (iii) developing models that condition on non-local context, in particular discourse structure, to improve the state of the art in high-resource scenarios.
[The workshop team members are: Chris Dyer (leader), Jacob Eisenstein (co-lead), Trevor Cohn (co-lead), Kaisheng Yao, Reza Haffari, Kevin Duh, Gaurav Kumar, Yangfeng Ji, Austin Matthews, Yi Luan, Ekaterina Vylomova, Lingpeng Kong, Uriel Mandujano, Cynthia Gan, Philipp Koehn, Sanjeev Khudanpur.]
Kevin Duh is a senior research scientist at the Johns Hopkins University Human Language Technology Center of Excellence (JHU HLTCOE). He is also an assistant research professor in the Department of Computer Science. Previously, he was assistant professor at the Nara Institute of Science and Technology (2012-2015) and research associate at NTT CS Labs (2009-2012). He received his B.S. in 2003 from Rice University, and PhD in 2009 from the University of Washington, both in Electrical Engineering. His research interests lie at the intersection of Natural Language Processing and Machine Learning, in particular on areas relating to machine translation, semantics, and deep learning.