We describe a novel approach to machine translation that combines the strengths of the two leading corpus-based approaches: Phrasal SMT and EBMT. We use a syntactically informed d...
When faced with many documents, people often use systems that characterize documents as read or unread. Most email and document management systems treat this distinction as a bina...
Translation of proper names is generally recognized as a significant problem in many multi-lingual text and speech processing applications. Even when large bilingual lexicons use...
We present a novel probabilistic multiple cause model for binary observations. In contrast to other approaches, the model is linear and it infers reasons behind both observed and ...
Low-density languages raise difficulties for standard approaches to natural language processing that depend on large online corpora. Using Persian as a case study, we propose a no...