AUTOMATIC EXTRACTION OF MULTILINGUAL DICTIONARY ITEMS FROM NON-PARALLEL, MULTILINGUAL, SEMI-STRUCUTRED DATA

• US 20150248400A1
• Filed: 02/28/2014
• Published: 09/03/2015
• Est. Priority Date: 02/28/2014
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Sawaf, Hassan
• Granted Patent: US 9,530,161 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/903 Querying for retrieval from the web G06F16/953
• 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 40/42 Data-driven translation
• CPC Class Codes: G06F 40/44 Statistical methods, e.g. probability models
• CPC Class Codes: G06F 40/45 Example-based machine translation; Alignment
• CPC Class Codes: G06F 40/49 using very large corpora, e.g. the web
• CPC Class Codes: G06F 40/51 Translation evaluation
• 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: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06Q 30/0609 Buyer or seller confidence or verification

Abstract

User interfaces receive a first plurality of user queries and result sets that are in a category, exhibit a constraint, and exhibit user behavior. Also received are a second plurality of user queries and result sets that that are in the category, exhibit the constraint, and exhibit user behavior. The second user queries and results are received either from a plurality of user interfaces coupled to a second system, or from the second system itself. Responsive to detecting that the first plurality of user queries and result sets and the second plurality of user queries and result sets satisfy respective thresholds, a signal indicates that at least one of the first plurality of user queries and at least one of the second plurality of user queries are translations of each other.

Claims

1. A method of machine translation comprising:

receiving, from a plurality of hardware computer processors, a first plurality of user queries and result sets that are in a category, that exhibit a constraint, and that exhibit a first group of user behavior;

receiving a second plurality of user queries and result sets that that are in the category, that exhibit the constraint, and that exhibit a second group of user behavior;

detecting that the first plurality of user queries and result sets and the second plurality of user queries and result sets satisfy respective thresholds; and

presenting at a user interface at least one of the first plurality of user queries as a translation of at least one of the second plurality of user queries.

2. The method of claim 1, the plurality of hardware computer processors being coupled to a first system.

4. The method of claim 1, the second plurality user queries and result sets being received from a second system.

5. The method of claim 1, the constraint comprising one of aspects, a bar code and a seller.

6. The method of claim 1, the first group of user behavior and the second group of user behavior comprising positive behavior, potentially negative behavior and clearly negative behavior.

7. The method of claim 1, the respective thresholds comprising a first percentage of the plurality of the first user queries that are satisfied by result sets responsive to the plurality of first user queries and a second percentage of the second plurality of user queries that are satisfied by result sets responsive to the plurality of second user queries, the satisfaction based on positive user behavior, potentially negative user behavior, and clearly negative user behavior, the first percentage and the second percentage being statistically significant.

8. One or more computer-readable hardware storage device having embedded therein a set of instructions which, when executed by one or more processors of a computer, causes the computer to execute operations comprising:

receiving a first plurality of user queries and result sets that are in a category, that exhibit a constraint, and that exhibit a first group of user behavior;

receiving a second plurality of user queries and result sets that that are in the category, that exhibit the constraint, and that exhibit a second group of user behavior;

detecting that the first plurality of user queries and the second plurality of user queries satisfy respective thresholds; and

presenting at a user interface at least one of the first plurality of user queries as a translation of at least one of the second plurality of user queries.

3. The method of claim 11, the second plurality of user queries and result sets being received from a plurality of hardware computer processors coupled to a second system.

9. The one or more computer-readable hardware storage device of claim 8, the first plurality of user queries and result sets being received from plurality of hardware computer processors that are coupled to a first system.

10. The one or more computer-readable hardware storage device of claim 8, the second plurality of user queries and result sets being received from a plurality of hardware computer processors coupled to a second system.

11. The one or more computer-readable hardware storage device of claim 8, the second plurality user queries and result sets being received from a second system.

12. The one or more computer-readable hardware storage device of claim 8, the constraint comprising one of aspects, a bar code and a seller.

13. The one or more computer-readable hardware storage device of claim 8, the first group of user behavior and the second group of user behavior comprising positive behavior, potentially negative behavior and clearly negative behavior.

14. The one or more computer-readable hardware storage device of claim 8, the respective thresholds comprising a first percentage of the plurality of first user queries that are satisfied by result sets responsive to the plurality of first user queries and a second percentage of the second plurality of user queries that are satisfied by result sets responsive to the plurality of second user queries, the satisfaction based on positive user behavior, potentially negative user behavior, and clearly negative user behavior, the first percentage and the second percentage being statistically significant.

15. A system comprising:

one or more computer processors and storage configured to;

execute a first module that comprises computer instructions to receive a first plurality of user queries and result sets that are in a category, that exhibit a constraint, and that exhibit a first group of user behavior;

execute a second module that comprises computer instructions to receive a second plurality of user queries and result sets that that are in the category, that exhibit the constraint, and that exhibit a second group of user behavior;

execute a third module that comprises computer instructions to detect that the first plurality of user queries and result sets and the second plurality of user queries and result sets satisfy respective thresholds; and

execute a fourth module that comprises computer instructions to present at a user interface at least one of the first plurality of user queries as a translation of at least one of the second plurality of user queries.

16. The system of claim 15, the first plurality of user queries and result sets being received from a plurality of hardware computer processors that are coupled to a first system.

17. The system of claim 15, the second plurality of user queries being received from a plurality of hardware computer processors coupled to a second system or from the second system.

18. The system of claim 15, the constraint comprising one of aspects, a bar code and a seller.

19. The system of claim 15, the first group of user behavior and the second group of user behavior comprising positive behavior, potentially negative behavior and clearly negative behavior.

20. The system of claim 15, the respective thresholds comprising a first percentage of the plurality of the first user queries that are satisfied by result sets responsive to the plurality of first user queries and a second percentage of the second plurality of user queries that are satisfied by result sets responsive to the second plurality of user queries, the first percentage and the second percentage being statistically significant.