Automatic machine translation using user feedback

• US 9,569,526 B2
• Filed: 02/28/2014
• Issued: 02/14/2017
• Est. Priority Date: 02/28/2014
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Sawaf, Hassan
• Primary Examiner(s): Bowen, Richard
• Application Number:
  US14/194,582
• Publication Number:
  US 20150248457A1
• Time in Patent Office: 1,082 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/2452 Query translation
• CPC Class Codes: G06F 16/3337 Translation of the query language, e.g. Chinese to English
• CPC Class Codes: G06F 40/44 Statistical methods, e.g. probability models
• 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 30/0282 Rating or review of business operators or products
• CPC Class Codes: G06Q 30/0613 Third-party assisted
• CPC Class Codes: G06Q 30/0625 Directed, with specific intent or strategy

Abstract

In a publication system, such as an ecommerce system, machine translation translates a query in a first language to a second language to query an ecommerce database maintained in the second language and obtain a result set responsive to the query. Human activity feedback relating to the result set is detected. If the feedback is positive the system increases the probability that the translation is correct. If the feedback is negative the system decreases the probability that the translation is correct. For positive feedback, the system detects whether a clue is recognized in the query. If a clue is recognized the system increases the value of the clue for making the translation. The system may detect the identity of the product in the query, accesses the product vendor website that is maintained in the first language, and detect information that is in the first language for use translation process.

Claims

1. A computer implemented method for machine translation comprising:

receiving, via an electronic communication channel, from a user interface at a client machine, a first query in a first language, the first query describing a product or a service;

translating the first query into a second language wherein correctness of the translation of the first query into the second language is based on a probability;

querying, using the first query, translated to the second language, an ecommerce database maintained in the second language;

obtaining a result set responsive to the querying;

translating the obtained result set to the first language;

transmitting the translated result set, via the electronic communication channel, to the user interface at the client machine;

determining, via the electronic communication channel, from the user interface at the client machine user action after the user is presented with the result set, the user action comprising user feedback other than a direct indication of the correctness of the translation of the first query into the second language;

determining whether the user feedback is positive or negative with respect to purchase of the product or the service;

responsive to determining that the user feedback is positive, increasing the probability on which the correctness of the translation of the first query into the second language was based;

responsive to determining that the user feedback is negative, decreasing the probability on which the correctness of the translation of the first query into the second language was based; and

receiving a subsequent query in the first language and translating the subsequent query into the second language based on one of the increased probability or the decreased probability.

2. The method of claim 1, the feedback being one of explicit human feedback and implicit human feedback.

3. The method of claim 1 further comprising, responsive to determining that the feedback is positive, detecting a clue in the first query, the clue comprising a plurality of translated words in the second language that result in the positive user feedback and increasing a value of the clue for making the translation from the first language to the second language.

4. The method of claim 3 further comprising, responsive to determining that the feedback is negative, detecting a clue in the first query, the clue comprising a plurality of translated words that result in the negative user feedback, and decreasing the value of the clue for making the translation from the first language to the second language.

5. The method of claim 1 further comprising

detecting the identity of the product or service in the first query;

accessing the product or service vendor website that is maintained in the first language;

detecting from the vendor website information that is in the first language that relates to the product or service; and

using the information in a translation process.

6. 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, via an electronic communication channel, from a user interface at a client machine, a first query in a first language, the first query describing a product or a service;

translating the first query into a second language wherein correctness of the translation of the first query into the second language is based on a probability;

querying, using the first query, translated to the second language, an ecommerce database maintained in the second language;

obtaining a result set responsive to the querying;

translating the obtained result set to the first language;

transmitting the translated result set via the electronic communication channel to the user interface at the client machine;

determining, via the electronic communication channel, from the user interface at the client machine user action after the user is presented with the result set, the user action comprising user feedback other than a direct indication of the correctness of the translation of the first query into the second language;

determining whether the user feedback is positive or negative with respect to purchase of the product or the service;

responsive to determining that the user feedback is positive, increasing the probability on which the correctness of the translation of the first query into the second language was based;

responsive to determining that the user feedback is negative, decreasing the probability on which the correctness of the translation of the first query into the second language was based; and

receiving a subsequent query in the first language and translating the subsequent query into the second language based on one of the increased probability or the decreased probability.

7. The one or more computer-readable hardware storage device of claim 6, the feedback being one of explicit human feedback and implicit human feedback.

8. The one or more computer-readable hardware storage device of claim 6, the operations further comprising, responsive to determining that the feedback is positive, detecting a clue in the first query, the clue comprising a plurality of translated words in the second language that result in the positive user feedback and increasing a value of the clue for making the translation from the first language to the second language.

9. The one or more computer-readable hardware storage device of claim 8, the operations further comprising, responsive to determining that the feedback is negative, detecting a clue in the first query, the clue comprising a plurality of translated words that result in the negative user feedback and decreasing the value of the clue for making the translation from the first language to the second language.

10. The one or more computer-readable hardware storage device of claim 6, the operations further comprising

detecting the identity of the product or service in the first query;

accessing the product or service vendor website that is maintained in the first language;

detecting from the vendor website information in the first language that relates to the product or service; and

using the information in a translation process.

11. A system for machine translation comprising one or more hardware processors configured to include:

one or more computer processor and storage configured to

receive, via an electronic communication channel, from a user interface a client machine, a first query in a first language, the query describing a product or a service;

translate the first query into a second language wherein correctness of the translation of the first query into the second language is based on a probability;

query, using the first query, translated to the second language, an ecommerce database maintained in the second language;

obtain a result set responsive to the query of the ecommerce system maintained in the second language;

translate the obtained result set into the second language;

transmit the translated result set via the electronic communication channel to the user interface at the client machine;

determine, via the electronic communication channel, from user interface at the client machine user action after the user is presented with the result set, the user action comprising user feedback other than a direct indication of the correctness of the translation of the first query into the second language;

determine whether the user feedback is positive or negative with respect to purchase of the product or the service;

responsive to a determination that the user feedback is positive, increase the probability on which the correctness of the translation of the first query into the second language was based;

responsive to a determination that the user feedback is negative, decrease the probability on which the correctness of the translation of the first query into the second language was based; and

receive a subsequent query in the first language and translate the subsequent query into the second language based on one of the increased probability or the decreased probability.

12. The system of claim 11, the feedback being one of explicit human feedback and implicit human feedback.

13. The system of claim 11, the one or more computer processor and storage further configured to, responsive to a determination that the feedback is positive, detect a clue in the first query, the clue comprising a plurality of translated words in the second language that result in the positive user feedback, and increase a value of the clue for making the translation from the first language to the second language.

14. The system of claim 11, the one or more computer processor and storage further configured to

detect the identity of the product or service in the first query;

access the product or service vendor website that is maintained in the first language;

detect from the vendor website information relating to the product or service; and

use the information in a translation process.

15. The system of claim 11, the one or more computer processor and storage further configured to, responsive to a determination that the feedback is negative, detect a clue in the first query, the clue comprising a plurality of translated words in the second language that result in the negative user feedback, and decrease a value of the clue for making the translation from the first language to the second language.