Text translation using contextual information related to text objects in translated language

• US 9,779,439 B2
• Filed: 06/02/2016
• Issued: 10/03/2017
• Est. Priority Date: 11/13/2013
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Chelly, Yan
• Primary Examiner(s): Opsasnick, Michael N
• Application Number:
  US15/171,476
• Publication Number:
  US 20160275587A1
• Time in Patent Office: 488 Days
• Field of Search: 704 2, 704270, 704277
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 40/205 Parsing
• 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
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06Q 30/0623 Item investigation

Abstract

In an example embodiment, a memory stores a database of text objects having textual information pertaining to at least one of a plurality of documents, and contextual information about the documents. A translation module then is configured to translate text from a first user from a first language to a second language, the text pertaining to a first of the plurality of documents. A context ranking module is configured to locate, in the database, a plurality of text objects, in the second language, having text similar to the translated text, and to rank the plurality of text objects having text similar to the translated text based on a comparison of contextual information about the first document and the contextual information stored in the database for documents corresponding to the plurality of text objects having text similar to the translated text.

Claims

1. An apparatus comprising:

a memory storing a database of text objects, each text object comprising textual information pertaining to at least one of a plurality of documents, the database further including contextual information about the documents;

of the plurality of documents;

a translation module executable by a processor and configured to translate text from a first user from a first language to a second language, the text pertaining to a first of the plurality of documents;

a context ranking module configured to locate, in the database, a plurality of text objects, in the second language, having text similar to the translated text, and to rank the plurality of text objects having text similar to the translated text based on a comparison of contextual information about the first document and the contextual information stored in the database for documents corresponding to the plurality of text objects similar to the translated text;

the translation module further configured to translate at least one of the ranked plurality of text objects to the first language; and

a display module presenting the translated at least one of the ranked plurality of text objects to the first user.

2. The apparatus of claim 1, further comprising a feedback module configured to receive feedback from the first user used to select one of the subset of the ranked plurality of text objects to be used in the ecommerce service.

3. The apparatus of claim 2, wherein the feedback includes an explicit selection of one of the subset of the ranked plurality of text objects by the first user.

4. The apparatus of claim 2, wherein the feedback includes scores assigned to a plurality of the ranked plurality of text objects.

5. The apparatus of claim 2, wherein the context ranking module is further configured to utilize the feedback in future rankings of text objects.

6. A method comprising:

receiving text from a first user, the text in a first language and pertaining to a first of a plurality of documents;

retrieving contextual information about the first of the plurality of documents;

translating the text to a second language;

locating, in a database, a plurality of text objects, in the second language, similar to the translated text, each text object comprising textual information pertaining to at least one listing;

ranking the plurality of text objects similar to the translated text based on a comparison of the contextual information about the first of the plurality of documents and contextual information stored in the database for documents similar to the translated text;

translating at least one of the ranked plurality of text objects to the first language; and

presenting a subset of the ranked plurality of text objects to the first user.

7. The method of claim 6, wherein the text from the first user is a question regarding a product.

8. The method of claim 7, wherein the contextual information is a category for the product.

9. The method of claim 7, wherein the contextual information includes past sales information.

10. The method of claim 7, wherein the contextual information includes product description information.

11. The method of claim 7, wherein the contextual information includes one or more images of the product.

12. The method of claim 6, wherein the translating the text to a second language includes passing the text to an application program interface (API) for a text translation service.

13. The method of claim 6, wherein the translating the text to a second language and the translating at least one of the ranked plurality of text objects to the first language both utilize a single translation module.

14. A non-transitory machine-readable storage medium having embodied thereon instructions executable by one or more machines to perform operations comprising:

receiving text from a first user, the text in a first language and pertaining to a first of a plurality of documents;

retrieving contextual information about the first of the plurality of documents;

translating the text to a second language;

locating, in a database, a plurality of text objects, in the second language, similar to the translated text, each text object comprising textual information pertaining to at least one listing;

ranking the plurality of text objects similar to the translated text based on a comparison of the contextual information about the first of the plurality of documents and contextual information stored in the database for documents similar to the translated text;

translating at least one of the ranked plurality of text objects to the first language; and

presenting a subset of the ranked plurality of text objects to the first user.

15. The non-transitory machine-readable storage medium of claim 14, wherein the text from the first user is a question regarding a product.

16. The non-transitory machine-readable storage medium of claim 15, wherein the contextual information is a category for the product.

17. The non-transitory machine-readable storage medium of claim 15, wherein the contextual information includes past sales information.

18. The non-transitory machine-readable storage medium of claim 15, wherein the contextual information includes product description information.

19. The non-transitory machine-readable storage medium of claim 15, wherein the contextual information includes one or more images of the product.

20. The non-transitory machine-readable storage medium of claim 15, wherein the translating the text to a second language and the translating at least one of the ranked plurality of text objects to the first language both utilize a single translation module.