Abstract:
We propose to use meaning-equivalent semantics as foundation for developing novel understanding, generation, translation, and evaluation algorithms. We discuss work that assesses the ability of monolingual and multilingual speakers to create large-scale, meaning-equivalent representations and the utility of these representations for automatically estimating the quality of machine translation technology and the proficiency of professional translators. We also discuss deficiencies of existing semantic representations and propose means to eliminate them.
Bio:
Daniel Marcu is the Chief Technology Officer of SDL Language Technologies and a Research Project Leader at the Information Sciences Institute, University of Southern California. His published work includes an MIT Press book and more than 100 peer reviewed articles, two of which have received best paper awards. Daniel Marcu has also co-founded Language Weaver Inc., which was acquired by SDL plc. in 2010.