IP Library › Granted Patent US 9,081,762
Granted Patent B2
US 9,081,762 · App. 13/548,231 · Granted Jul 14, 2015

Phrase-based dictionary extraction and translation quality evaluation

Inventors: Enyuan Wu (Bellevue, WA); Beom Seok Oh (Sammamish, WA); Alan Michael (Monroe, WA); Kevin O'Donnell (Kirkland, WA)
G06F17/2735G06F17/2818G06F17/2827G06F17/2854
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,081,762
App. No.
13/548,231
Granted
Jul 14, 2015
Kind
B2
Abstract

In one embodiment, a translator quality assurance system may rate a translation using a mapping chart. A data interface 150 may access a translation dictionary matching a source language to a target language. A processor 120 may map automatically a sentence pair having a source sentence 310 in a source language and a target sentence 320 in a target language at a linguistic level using the translation dictionary. A user output device 170 may display a translation quality report of the target sentence 320.

Claims (43)

1. A machine-implemented method, comprising:

maintaining, in a translation quality assurance system, a translation dictionary matching a source language to a target language;

mapping automatically with the translation quality assurance system a sentence pair having a source sentence in the source language and a target sentence in the target language at a linguistic level using the translation dictionary;

identifying an unmapped word as a compound word if an unmapped source word has a translation that is a prefix of the compound word; and

generating automatically with the translation quality assurance system a translation quality report describing a translation quality of the sentence pair.

2. The method of claim 1 , further comprising:

mapping a source word of the source sentence to a target element of the target sentence.

3. The method of claim 1 , further comprising:

mapping a source phrase of the source sentence to a target element of the target sentence prior to mapping a source word.

4. The method of claim 1 , further comprising:

identifying a noisy word for deferred matching.

5. The method of claim 1 , further comprising:

using fuzzy matching to map an unmatched element.

6. The method of claim 1 , further comprising:

mapping the compound word to matching elements using fuzzy matching.

7. The method of claim 1 , further comprising:

importing the translation dictionary from a dictionary source.

8. The method of claim 1 , further comprising:

updating the translation dictionary based on a user correction.

9. The method of claim 1 , further comprising:

maintaining a specialty translation dictionary.

10. A tangible computer-readable storage device having a set of instructions detailing a method stored thereon that when executed by one or more processors cause the one or more processors to perform the method, the method comprising:

maintaining a translation dictionary matching a source language to a target language;

mapping automatically a sentence pair having a source sentence in the source language and a target sentence in the target language at a linguistic level using the translation dictionary;

identifying an unmapped word as a compound word if an unmapped source word has a translation that is a prefix of the compound word; and

generating automatically a translation quality report describing a translation quality of the sentence pair.

11. The tangible computer-readable storage device of claim 10 , wherein the method further comprises:

mapping a source phrase of the source sentence to a target element of the target sentence prior to mapping a source word.

12. The tangible computer-readable storage device of claim 10 , wherein the method further comprises:

identifying a noisy word for deferred matching.

13. The tangible computer-readable storage device of claim 10 , wherein the method further comprises:

using fuzzy matching to map an unmatched element.

14. The tangible computer-readable storage device of claim 10 , wherein the method further comprises:

mapping the compound word to matching elements using fuzzy matching.

15. A translation quality assurance system, comprising:

a data storage that accesses a translation dictionary matching a source language to a target language;

a processor that maps automatically a sentence pair having a source sentence in the source language and a target sentence in the target language at a linguistic level using the translation dictionary, identifies an unmapped word as a compound word if an unmapped source word has a translation that is a prefix of the compound word, and generates a translation quality report describing a translation quality of the sentence pair; and

a user output device that displays the translation quality report of the sentence pair.

16. The translation quality assurance system of claim 15 , wherein the processor calculates a translation confidence score for the sentence pair.

17. The translation quality assurance system of claim 15 , wherein the translation quality report displays a mapping chart between the target sentence and the source sentence.

18. The translation quality assurance system of claim 17 , wherein the translation quality report color codes the mapping chart.

19. The translation quality assurance system of claim 15 , wherein the processor produces the translation quality report in realtime.

20. The translation quality assurance system of claim 15 , wherein the processor maps the compound word to matching elements using fuzzy matching.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 9, 2014
From: MICROSOFT CORPORATION
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 034544/0541 →
CORRECTIVE ASSIGNMENT TO CORRECT THE FOURTH ASSIGNOR NAME ON THE COVERSHEET PREVIOUSLY RECORDED ON REEL 028553 FRAME 0808. ASSIGNOR(S) HEREBY CONFIRMS THE NAME OF FOURTH ASSIGNOR IS KEVIN O'DONNELL.. Recorded Jul 17, 2013
From: WU, ENYUAN; OH, BEOM SEOK; MICHAEL, ALAN; O'DONNELL, KEVIN
To: MICROSOFT CORPORATION
Reel/Frame 030821/0676 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 13, 2012
From: WU, ENYUAN; OH, BEOM SEOK; MICHAEL, ALAN; DONNELL, KEVIN O
To: MICROSOFT CORPORATION
Reel/Frame 028553/0808 →
Continuity (1)
Related Publication 20140019113A1 · Jan 16, 2014