Determining corresponding terms written in different formats

• US 9,734,197 B2
• Filed: 03/06/2014
• Issued: 08/15/2017
• Est. Priority Date: 07/06/2000
• Status: Expired due to Term

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Mittal, Vibhu, Ghemawat, Sanjay, Ponte, Jay M., Bauer, John A., Sahami, Mehran
• Primary Examiner(s): Chen, Susan
• Application Number:
  US14/199,249
• Publication Number:
  US 20140188454A1
• Time in Patent Office: 1,258 Days
• CPC Class Codes: G06F 16/2452 Query translation
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries
• CPC Class Codes: G06F 16/3332 Query translation
• CPC Class Codes: G06F 16/972 Access to data in other repository systems, e.g. legacy data or dynamic Web page generation
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 40/12 Use of codes for handling textual entities
• CPC Class Codes: G06F 40/237 Lexical tools

Abstract

Methods and apparatus consistent with the invention allow a user to submit an ambiguous search query and to receive relevant search results. Queries can be expressed using character sets and/or languages that are different from the character set and/or language of at least some of the data that is to be searched. A translation between these character sets and/or languages can be performed by examining the use of terms in aligned text. Probabilities can be associated with each possible translation. Refinements can be made to these probabilities by examining user interactions with the search results.

Claims

1. A computer-implemented method comprising:

receiving an input term in a first language format;

identifying two different groups of hyperlinks that each link to a same plurality of intermediary documents, wherein the different groups of hyperlinks have anchor texts in different respective language formats, including;

identifying a first group of hyperlinks each having a respective first anchor text that includes the input term in the first language format, and

identifying a second group of hyperlinks each having a respective second anchor text in a second language format;

determining, from all of the second anchor texts of the second group of hyperlinks, a second term in the second language format that corresponds to the input term in the first language format, including;

computing, by one or more computers, a total count of terms, including duplicates, occurring in all of the second anchor texts of the second group of hyperlinks,

computing, by one or more computers, a respective individual count of occurrences, in all of the second anchor texts of the second group of hyperlinks, of each of a plurality of terms in the second language format that occur in all of the second anchor texts of the second group of hyperlinks,

computing, by one or more computers, a respective score for each of the plurality of terms in the second language format that occur in all of the second anchor texts of the second group of hyperlinks, including comparing, for each term of the plurality of terms in the second language format that occur in all of the second anchor texts of the second group of hyperlinks, the respective individual count for the term to the total count of terms occurring in the second anchor texts of the second group of hyperlinks, and

designating a highest-scoring term among the plurality of terms in the second language format that occur in all of the second anchor texts of the second group of hyperlinks as the second term in the second language format that corresponds to the input term in the first language format;

receiving a first query having the input term in the first language format;

generating a revised query that includes the second term in the second language format;

obtaining search results using the revised query; and

providing the search results obtained using the revised query in response to receiving the first query.

2. The method of claim 1, wherein the first language format comprises a first character set, and the second language format comprises a different, second character set.

3. The method of claim 2, wherein the first language format is romaji, romaja, or pinyin;

and wherein the second character set is katakana, hiragana, kanji, hangul, hanja, or traditional Chinese characters.

4. The method of claim 1, wherein the first language format comprises a first language and the second language format comprises a different, second language.

5. The method of claim 1, wherein the documents comprise web pages.

6. The method of claim 1, wherein obtaining the search results using the revised query comprises:

searching a database for information in the second language format using the revised query having the second term in the second language format.

7. A computer program product embodied on a non-transitory computer-readable medium, the computer program product including instructions, which when executed by a computer system, are operable to cause the computer system to perform operations comprising:

receiving an input term in a first language format;

identifying two different groups of hyperlinks that each link to a same plurality of intermediary documents, wherein the different groups of hyperlinks have anchor texts in different respective language formats, including;

identifying a first group of hyperlinks each having a respective first anchor text that includes the input term in the first language format, and

identifying a second group of hyperlinks each having a respective second anchor text in a second language format;

determining, from all of the second anchor texts of the second group of hyperlinks, a second term in the second language format that corresponds to the input term in the first language format, including;

computing a total count of terms, including duplicates, occurring in all of the second anchor texts of the second group of hyperlinks,

computing a respective individual count of occurrences, in all of the second anchor texts of the second group of hyperlinks, of each of a plurality of terms in the second language format that occur in all of the second anchor texts of the second group of hyperlinks,

computing a respective score for each of the plurality of terms in the second language format that occur in all of the second anchor texts of the second group of hyperlinks including comparing, for each term of the plurality of terms in the second language format that occur in all of the second anchor texts of the second group of hyperlinks, the respective individual count for the term to the total count of terms occurring in the second anchor texts of the second group of hyperlinks, and

designating a highest-scoring term among the plurality of terms in the second language format that occur in all of the second anchor texts of the second group of hyperlinks as the second term in the second language format that corresponds to the input term in the first language format;

receiving a first query having the input term in the first language format;

generating a revised query that includes the second term in the second language format;

obtaining search results using the revised query; and

providing the search results obtained using the revised query in response to receiving the first query.

8. The computer program product of claim 7, wherein the first language format comprises a first character set, and the second language format comprises a different, second character set.

9. The computer program product of claim 8, wherein the first language format is romaji, romaja, or pinyin;

and wherein the second character set is katakana, hiragana, kanji, hangul, hanja, or traditional Chinese characters.

10. The computer program product of claim 7, wherein the first language format comprises a first language and the second language format comprises a different, second language.

11. The computer program product of claim 7, wherein the documents comprise web pages.

12. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

receiving an input term in a first language format;

identifying two different groups of hyperlinks that each link to a same plurality of intermediary documents, wherein the different groups of hyperlinks have anchor texts in different respective language formats, including;

identifying a first group of hyperlinks each having a respective first anchor text that includes the input term in the first language format, and

identifying a second group of hyperlinks each having a respective second anchor text in a second language format;

determining, from all of the second anchor texts of the second group of hyperlinks, a second term in the second language format that corresponds to the input term in the first language format, including;

computing a total count of terms, including duplicates, occurring in all of the second anchor texts of the second group of hyperlinks,

computing a respective individual count of occurrences, in all of the second anchor texts of the second group of hyperlinks of each of a plurality of terms in the second language format that occur in all of the second anchor texts of the second group of hyperlinks,

computing a respective score for each of the plurality of terms in the second language format that occur in all of the second anchor texts of the second group of hyperlinks, including comparing, for each term of the plurality of terms in the second language format that occur in all of the second anchor texts of the second group of hyperlinks, the respective individual count for the term to the total count of terms occurring in all of the second anchor texts of the second group of hyperlinks, and

designating a highest-scoring term among the plurality of terms in the second language format that occur in all of the second anchor texts of the second group of hyperlinks as the second term in the second language format that corresponds to the input term in the first language format;

receiving a first query having the input term in the first language format;

generating a revised query that includes the second term in the second language format;

obtaining search results using the revised query; and

providing the search results obtained using the revised query in response to receiving the first query.

13. The system of claim 12, wherein the first language format comprises a first character set, and the second language format comprises a different, second character set.

14. The system of claim 13, wherein the first language format is romaji, romaja, or pinyin;

and wherein the second character set is katakana, hiragana, kanji, hangul, hanja, or traditional Chinese characters.

15. The system of claim 12, wherein the first language format comprises a first language and the second language format comprises a different, second language.

16. The system of claim 12, wherein the documents comprise web pages.