Query Language Identification

• US 20110231423A1
• Filed: 04/19/2007
• Published: 09/22/2011
• Est. Priority Date: 04/19/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Lopiano, Fabio
• Granted Patent: US 8,442,965 B2
• Time in Patent Office: Days
• US Class Current: 707/760
• CPC Class Codes: G06F 16/2452 Query translation
• CPC Class Codes: G06F 16/3338 Query expansion
• CPC Class Codes: G06F 40/263 Language identification

Abstract

Methods, systems, and apparatus, including computer program products, for identifying the language of a search query. In one embodiment, the language of each term of a query is determined from the query terms and the language of the user interface a user used to enter the query. In another embodiment, an automatic interface language classifier is generated from a collection of past queries each submitted by a user. In some embodiments, a score is determined for each of multiple languages, each score indicating a likelihood that the query language is the corresponding one of the multiple languages.

Claims

1-27. -27. (canceled)

28. A computer implemented method, comprising:

receiving, in a system comprising one or more computers, through a user interface, a search query comprising one or more query terms, the user interface having an interface language, where the interface language is a natural language in which the user interface presents information; and

determining, by the system, a query language of the query from the query, the interface language, and a plurality of query records stored by the system, the query language being a natural language;

where determining the query language of the query further comprises;

for each of multiple languages,

calculating a first score for each query term and the respective language, each first score indicating the likelihood that the respective query term is in the respective language, where the first score is calculated based on a plurality of documents, each document having an associated natural language,

calculating a second score for the respective language, the second score indicating the likelihood that the query is in the respective language given the user interface through which the query was received, where the second score is calculated based on the plurality of query records, and

calculating a third score for the respective language, the third score being a combination of the first scores for the respective language and the second score for the respective language; and

selecting the query language based on the third scores for the multiple languages.

29. The method of claim 28 where calculating the first score includes:

for each query term;

determining the first score based on a number of times each respective query term appears in the plurality documents in the respective language, the plurality of documents being from a corpus of documents, each document in the corpus of documents being labeled as containing content in one of the multiple languages.

30. The method of claim 28 where the plurality of query records is associated with the user interface, each query record referring to a query received through the user interface, each query record associating the query received with one or more result documents, each result document having an associated natural language.

31. The method of claim 30, where determining the query language further comprises:

using an interface language classifier to determine a respective likelihood of the languages that the query is in given the user interface that received the query.

32. A computer program product, encoded on a machine-readable storage device, operable to cause data processing apparatus to perform operations comprising:

receiving, in a system comprising one or more computers, through a user interface, a search query comprising one or more query terms, the user interface having an interface language, where the interface language is a natural language in which the user interface presents information; and

determining, by the system, a query language of the query from the query, the interface language, and a plurality of query records stored by the system, the query language being a natural language;

where determining the query language of the query further comprises;

for each of multiple languages,

calculating a first score for each query term and the respective language, each first score indicating the likelihood that the respective query term is in the respective language, where the first score is calculated based on a plurality of documents, each document having an associated natural language,

calculating a second score for the respective language, the second score indicating the likelihood that the query is in the respective language given the user interface through which the query was received, where the second score is calculated based on the plurality of query records, and

calculating a third score for the respective language, the third score being a combination of the first scores for the respective language and the second score for the respective language; and

selecting the query language based on the third scores for the multiple languages.

33. The product of claim 32 where calculating the first score includes:

for each query term;

determining the first score based on a number of times each respective query term appears in the plurality documents in the respective language, the plurality of documents being from a corpus of documents, each document in the corpus of documents being labeled as containing content in one of the multiple languages.

34. The product of claim 32 where the plurality of query records is associated with the user interface, each query record referring to a query received through the user interface, each query record associating the query received with one or more result documents, each result document having an associated natural language.

35. The product of claim 34, where determining the query language further comprises:

using an interface language classifier to determine a respective likelihood of the languages that the query is in given the user interface that received the query.

36. A system comprising:

one or more computers configured to perform operations comprising;

receiving, in a system comprising one or more computers, through a user interface, a search query comprising one or more query terms, the user interface having an interface language, where the interface language is a natural language in which the user interface presents information; and

determining, by the system, a query language of the query from the query, the interface language, and a plurality of query records stored by the system, the query language being a natural language;

where determining the query language of the query further comprises;

for each of multiple languages,

calculating a first score for each query term and the respective language, each first score indicating the likelihood that the respective query term is in the respective language, where the first score is calculated based on a plurality of documents, each document having an associated natural language,

calculating a second score for the respective language, the second score indicating the likelihood that the query is in the respective language given the user interface through which the query was received, where the second score is calculated based on the plurality of query records, and

calculating a third score for the respective language, the third score being a combination of the first scores for the respective language and the second score for the respective language; and

selecting the query language based on the third scores for the multiple languages.

37. The system of claim 36 where calculating the first score includes:

for each query term;

determining the first score based on a number of times each respective query term appears in the plurality documents in the respective language, the plurality of documents being from a corpus of documents, each document in the corpus of documents being labeled as containing content in one of the multiple languages.

38. The system of claim 36 where the plurality of query records is associated with the user interface, each query record referring to a query received through the user interface, each query record associating the query received with one or more result documents, each result document having an associated natural language.

39. The system of claim 38, where determining the query language further comprises:

using an interface language classifier to determine a respective likelihood of the languages that the query is in given the user interface that received the query.