Masaki Hiroyo Itagaki

US Patent:

20090063126, Mar 5, 2009

Filed:

Aug 29, 2007

Appl. No.:

11/897197

Inventors:

Masaki Itagaki - Redmond WA, US
Takako Aikawa - Seattle WA, US
Xiaodong He - Issaquah WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06F 17/28

US Classification:

704 2

Abstract:

A method of determining the consistency of training data for a machine translation system is disclosed. The method includes receiving a signal indicative of a source language corpus and a target language corpus. A textual string is extracted from the source language corpus. The textual string is aligned with the target language corpus to identify a translation for the textual string from the target language corpus. A consistency index is calculated based on a relationship between the textual string from the source language corpus and the translation. An indication of the consistency index is stored on a tangible medium.

US Patent:

20100082324, Apr 1, 2010

Filed:

Sep 30, 2008

Appl. No.:

12/241123

Inventors:

Masaki Itagaki - Redmond WA, US
Takako Aikawa - Seattle WA, US

Assignee:

MICROSOFT CORPORATION - Redmond WA

International Classification:

G06F 17/28

US Classification:

704 2

Abstract:

A system described herein includes a receiver component that receives an output translation from a machine translation system, wherein the output translation is in a target language and is based at least in part upon an input to the machine translation system in a source language, and wherein the input to the machine translation system includes a first term in the source language and the output translation includes a second term in the target language that corresponds to the first term. The system additionally includes a replacer component in communication with the receiver component that accesses a dictionary of term correspondences, wherein the dictionary of term correspondences includes an indication that the input first term in the source language is desirably translated to a third term in the target language, and wherein the replacer component is configured to automatically replace the second term with the third term to modify the output translation.