Phrase to phrase joint probability model for statistical machine translation

• US 20040030551A1
• Filed: 03/27/2003
• Published: 02/12/2004
• Est. Priority Date: 03/27/2002
• Status: Active Grant

• Current Assignee: University of Southern California
• Original Assignee: University of Southern California
• Inventors: Marcu, Daniel, Wong, William, Koehn, Philipp, Knight, Kevin
• Granted Patent: US 7,454,326 B2
• Time in Patent Office: Days
• US Class Current: 704/240
• CPC Class Codes: G06F 40/44 Statistical methods, e.g. probability models
• CPC Class Codes: G06F 40/45 Example-based machine translation; Alignment

Abstract

A machine translation (MT) system may utilize a phrase-based joint probability model. The model may be used to generate source and target language sentences simultaneously. In an embodiment, the model may learn phrase-to-phrase alignments from word-to-word alignments generated by a word-to-word statistical MT system. The system may utilize the joint probability model for both source-to-target and target-to-source translation applications.

Claims

1. A method comprising:

training a phrase-based joint probability model with a parallel corpus comprising a plurality of parallel text segments in two languages.

2. The method of claim 1, further comprising:

determining high frequency n-grams in a sentence pair comprising E and F;

initializing a t-distribution table;

performing a Viterbi-based Expectation Maximum training procedure; and

deriving a conditional probability model.