Patents by Inventor Mikhail Zaslavskiy

Mikhail Zaslavskiy has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Phrase-based statistical machine translation as a generalized traveling salesman problem
    Patent number: 8504353
    Abstract: Systems and methods are described that facilitate phrase-based statistical machine translation (SMT) incorporating bigram (or higher n-gram) language models by modeling bi-phrases as nodes in a graph. Additionally, construction of a translation is modeled as a “tour” amongst the nodes of the graph, such that a translation solution is generated by treating the graph as a generalized traveling salesman problem (GTSP) and solving for an optimal tour. The overall cost of a tour is computed by adding the costs associated with the edges traversed during the tour. Thus, the described systems and methods map the SMT problem directly into a GTSP problem, which itself can be directly converted into a TSP problem.
    Type: Grant
    Filed: July 27, 2009
    Date of Patent: August 6, 2013
    Assignee: Xerox Corporation
    Inventors: Mikhail Zaslavskiy, Marc Dymetman, Nicola Cancedda
  • PHRASE-BASED STATISTICAL MACHINE TRANSLATION AS A GENERALIZED TRAVELING SALESMAN PROBLEM
    Publication number: 20110022380
    Abstract: Systems and methods are described that facilitate phrase-based statistical machine translation (SMT) incorporating bigram (or higher n-gram) language models by modeling bi-phrases as nodes in a graph. Additionally, construction of a translation is modeled as a “tour” amongst the nodes of the graph, such that a translation solution is generated by treating the graph as a generalized traveling salesman problem (GTSP) and solving for an optimal tour. The overall cost of a tour is computed by adding the costs associated with the edges traversed during the tour. Thus, the described systems and methods map the SMT problem directly into a GTSP problem, which itself can be directly converted into a TSP problem.
    Type: Application
    Filed: July 27, 2009
    Publication date: January 27, 2011
    Applicant: Xerox Corporation
    Inventors: Mikhail Zaslavskiy, Marc Dymetman, Nicola Cancedda