×

Hybrid machine translation

  • US 9,798,720 B2
  • Filed: 10/26/2009
  • Issued: 10/24/2017
  • Est. Priority Date: 10/24/2008
  • Status: Expired due to Fees
First Claim
Patent Images

1. A system for automatic translation, comprising:

  • at least one database for storing source and target text, rule based and statistical language models, and directed acyclic graphs (DAGS), wherein the rule based language models comprise syntactic, semantic and grammatical rule based models; and

    a hybrid machine translation engine, having a maximum entropy algorithm that is coupled to the rule based language models and the statistical language models, the maximum entropy algorithm translating source text in one natural human language into target text in another natural human language based on the rule based language models, the statistical language models, and the DAGS;

    wherein the hybrid machine translation engine is the only translation engine in the system.

View all claims
  • 7 Assignments
Timeline View
Assignment View
    ×
    ×