Content page URL translation

• US 8,942,973 B2
• Filed: 03/09/2012
• Issued: 01/27/2015
• Est. Priority Date: 03/09/2012
• Status: Active Grant

• Current Assignee: SDL Inc (RWS Holdings Plc)
• Original Assignee: Language Weaver, Inc. (RWS Holdings Plc)
• Inventors: Viswanathan, Narayanaswamy
• Primary Examiner(s): ALBERTALLI, BRIAN LOUIS
• Application Number:
  US13/417,071
• Publication Number:
  US 20130238310A1
• Time in Patent Office: 1,054 Days
• US Class Current: 704/5
• CPC Class Codes: G06F 16/9566 URL specific, e.g. using aliases, detecting broken or misspelled links
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation

Abstract

The present technology may translate a content of a web page such as content locator (e.g., a uniform resource locator (URL)) from a source language to a target language. The content locator may be associated with a content page. The translation may involve dividing the content locator into segment tokens in a first language, followed by translating, transliterating or not changing a segment token. The processed tokens are then reassembled in a second language. The translation may be provided by a translation module through a content page provided by a network browser.

Claims

1. A method for translating a content locator, the method comprising:

determining at least one segment of the content locator;

generating a plurality of possible transformations of the at least one segment;

calculating a context score for each of the plurality of possible transformations by comparing each of the possible transformations to subject matter included in a document associated with the content locator;

ranking each of the plurality of possible transformations by comparing the context scores of the plurality of possible transformations to one another;

transforming the at least one segment from a source language into a target language by at least one of translation or transliteration; and

transmitting the transformed at least one segment in the target language for display on a network browser of a client device.

2. The method according to claim 1, wherein determining comprises:

determining one or more words included in the content locator that are to be translated from the source language into the target language, each of the one or more words being separated from the content locator as a segment; and

analyzing the remaining portion of the content locator to determine one or more characters or words that are to be transliterated from the source language into the target language.

3. The method according to claim 1, further comprising:

integrating back into the content locator, the at least one segment which was transformed; and

transmitting the content locator having the integrated at least one segment to the client device.

4. The method according to claim 1, further comprising receiving an indication of a content locator that is to be translated, the indication generated by selection of the content locator by an input device coupled to the client device.

5. The method according to claim 1, wherein transformation comprises:

generating a trust value for the transformation of the at least one segment, the trust value including an accuracy for the transformation; and

utilizing the transformation of the at least one segment if the trust value for the at least one segment meets or exceeds a threshold value.

6. The method according to claim 1, wherein the content locator includes any of a uniform resource locator, a uniform resource indicator, a uniform resource name, a domain name, and combinations thereof.

7. The method according to claim 1, further comprising:

assigning a weight to each of the plurality of possible transformations, the weight being based upon a relative comparison of a possible transformation to a word in a parallel corpora; and

selecting a possible transformation with the highest weight based upon the comparison.

8. A method for transforming a content locator, the method comprising:

determining the content locator into two or more segments;

generating a plurality of possible transformations of the two or more segments;

calculating a context score for each of the plurality of possible transformations by comparing each of the possible transformations to subject matter included in a document associated with the content locator;

ranking each of the plurality of possible transformations by comparing the context scores of the plurality of possible transformations to one another;

transforming at least one of the two or more segments from a source language into at least one target language by at least one of translation or transliteration; and

combining the two or more segments together before transmitting the combined segments to a client device.

9. A system for translating a content locator, the system comprising:

a memory for storing executable instructions;

a processor for executing the executable instructions;

a translation module stored in memory and executable by the processor to;

determine at least one segment of the content locator; and

transform the at least one segment from a source language into a target language by at least one of translation or transliteration;

a quality prediction engine that;

calculates a context score for each of a plurality of possible transformations by comparing each of the possible transformations to subject matter included in a document associated with the content locator; and

ranks each of the plurality of possible transformations by comparing the context scores of the plurality of possible transformations to one another; and

a communications module stored in memory and executable by the processor to transmit the transformed at least one segment in the target language for display on a network browser of a client device.

10. The system according to claim 9, wherein the translation module further:

determines one or more words included in the content locator that are to be translated from the source language into the target language, each of the one or more words being identified as a segment; and

analyzes the remaining portion of the content locator to determine one or more characters or words that are to be transliterated from the source language into the target language.

11. The system according to claim 9, wherein the translation module further integrates into the content locator the at least one segment which was transformed;

and the communications module transmits the content locator having at least a portion that has been transformed from the source language into the target language.

12. The system according to claim 9, wherein the communications module receives an indication of a content locator that is to be translated, the indication generated by selection of the content locator by an input device coupled to the client device.

13. The system according to claim 9, wherein the quality prediction engine:

generates a trust value for the transformation of the at least one segment, the trust value including an accuracy for the transformation; and

utilizes the transformation of the at least one segment if the trust value for the at least one segment meets or exceeds a threshold value.

14. The system according to claim 13, wherein the quality prediction engine further:

assigns a weight to each of the plurality of possible transformations, the weight being based upon a relative comparison of a possible transformation to a word in a parallel corpora; and

selects a possible transformation with the highest weight based upon the comparison.

15. The system according to claim 9, wherein the content locator includes any of a uniform resource locator, a uniform resource indicator, a uniform resource name, a domain name, and combinations thereof.

16. The system according to claim 9, wherein the translation module includes a plugin that cooperates with a network browser that resides on the client device.

17. A non-transitory computer readable storage medium having a computer program embodied thereon, the computer program executable by a processor in a computing system to perform a method for translating a content locator, the method comprising:

determining at least one segment of the content locator;

generating a plurality of possible transformations of the at least one segment;

calculating a context score for each of the plurality of possible transformations by comparing each of the transformations to subject matter included in a document associated with the content locator;

ranking each of the plurality of possible transformations by comparing the context scores of the plurality of possible transformations to one another;

transforming the at least one segment from a source language into a target language by at least one of translation or transliteration; and

transmitting the transformed at least one segment in the target language for display on a network browser of a client device.