Method and system for detecting user intentions in retrieval of hint sentences

• US 7,562,082 B2
• Filed: 06/14/2005
• Issued: 07/14/2009
• Est. Priority Date: 09/19/2002
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Zhou, Ming
• Primary Examiner(s): Cottingham; John R.
• Assistant Examiner(s): Arjomandi; Noosha
• Application Number:
  US11/152,645
• Publication Number:
  US 20060142994A1
• Time in Patent Office: 1,491 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• 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: Y10S 707/99932 Access augmentation or optimizing
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface

Abstract

A method of constructing a confusion set database for use in detecting user query intentions includes obtaining a bilingual database having aligned word pairs in first and second languages. Second language word pairs in the bilingual database are aligned with corresponding correct translation first language word pairs. First language human translation word pairs corresponding to each of the second language word pairs in the bilingual database are obtained. Each first language human translation word pair for a particular second language word pair in the bilingual database is aligned with the correct translation first language word pair to define first language set pairs in the confusion set database. Methods, systems and computer readable medium for constructing the confusion set database and for retrieving sentences using the confusion set database are also disclosed.

Claims

1. A method of constructing a confusion set database for use in detecting user query intentions in the retrieval of sentences from a sentence database in response to the query, the method comprising:

a memory coupled to a processor;

obtaining a bilingual database having word pairs in first and second languages, wherein each of a plurality of word pairs in the second language in the bilingual database is aligned with a corresponding word pair in the first language in the bilingual database, the aligned word pair in the first language in the bilingual database being a correct translation word pair in the first language for the corresponding word pair in the second language;

using the processor to obtain, separately from the bilingual database, human translation word pairs in the first language corresponding to each of the plurality of word pairs in the second language in the bilingual database;

using the processor to align each human translation word pair in the first language with the correct translation word pair in the first language, both corresponding to the same word pair in the second language, to define first language set pairs in the confusion set database; and

using the processor to remove from the confusion set database first language set pairs in which the human translation word pair in the first language and the correct translation word pair in the first language, together defining the first language set pair, are the same and wherein removing from the confusion set database first language set pairs in which the human translation word pair in the first language and the correct translation word pair in the first language are the same comprises removing both the human translation word pair in tile first language and the corresponding correct translation word pair in the first language which together define the first language set pair.

2. The method of claim 1, wherein obtaining the bilingual database having word pairs in the first and second languages includes:

obtaining a word and sentence aligned bilingual corpus.

3. The method of claim 1, wherein obtaining the bilingual database having word pairs in the first and second languages includes:

obtaining a word aligned bilingual dictionary.

4. The method of claim 1, wherein using the processor to obtain human translation word pairs in the first language corresponding to each of the plurality of word pairs in the second language in the bilingual database further comprises:

performing human translation of each of the plurality of word pairs in the second language in the bilingual database into the human translation word pairs in the first language.

5. A tangible computer-storage medium having computer-executable instructions for performing steps comprising:

using a processor to obtain a bilingual database having word pairs in first and second languages, wherein each of a plurality of word pairs in the second language in the bilingual database is aligned with a corresponding word pair in the first language in the bilingual database, the aligned word pair in the first language in the bilingual database being a correct translation word pair in the first language for the corresponding word pair in the second language;

using the processor to obtain human translation word pairs in the first language corresponding to each of the plurality of word pairs in the second language in the bilingual database;

using the processor to align each human translation word pair in the first language with the correct translation word pair in the first language, both corresponding to the same word pair in the second language, to define first language set pairs in a confusion set database for use in detecting user query intentions in the retrieval of sentences from a sentence database in response to the query; and

using the processor to remove from the confusion set database first language set pairs in which the human translation word pair in the first language and the correct translation word pair in the first language, together defining the first language set pair, are the same, and wherein removing from the confusion set database first language set pairs in which the human translation word pair in the first language and the correct translation word pair in the first language are the same comprises removing both the human translation word pair in the first language and the corresponding correct translation word pair in the first language which together define the first language set pair.

6. The computer-storage medium of claim 5, wherein using the processor to align each human translation word pair in the first language with the correct translation word pair in the first language, both corresponding to the same word pair in the second language, to define the first language set pairs in the confusion set database further comprises:

determining which first language set pairs have a first language human translation word pair in the first language which differs from its corresponding correct translation word pair in the first language; and

inserting into the confusion set database only those first language set pairs in which the human translation word pair in the first language differs from its corresponding correct translation word pair in the first language.

11. The tangible computer-storage medium of claim 5, wherein using the processor to obtain the bilingual database having word pairs in the first and second languages includes:

obtaining a word and sentence aligned bilingual corpus.

12. The tangible computer-storage medium of claim 5, wherein using the processor to obtain the bilingual database having word pairs in the first and second languages includes:

obtaining a word aligned bilingual dictionary.

13. The tangible computer-storage medium of claim 5, wherein using the processor to obtain the human translation word pairs in the first language corresponding to each of the plurality of word pairs in the second language in the bilingual database further comprises:

performing human translation of each of the plurality of word pairs in the second language in the bilingual database into the human translation word pairs in the first language.

7. A method of constructing a confusion set database for use in detecting user query intentions in the retrieval of sentences from a sentence database in response to the query, the method comprising:

a memory coupled to a processor;

using the processor to obtain a bilingual database having word pairs in first and second languages, wherein each of a plurality of word pairs in the second language in the bilingual database is aligned with a corresponding word pair in the first language in the bilingual database, the aligned word pair in the first language in the bilingual database being a correct translation word pair in the first language for the corresponding word pair in the second language;

using the processor to obtain, separately from the bilingual database, human translation word pairs in the first language corresponding to each of the plurality of word pairs in the second language in the bilingual database; and

using the processor to align each human translation word pair in the first language for a particular second language word pair in the bilingual database with the correct translation word pair also aligned with the particular second language word pair in the bilingual database to define first language set pairs in the confusion set database, each first language set pair comprising an aligned human translation word pair and correct translation word pair both in the first language and both corresponding to the same second language word pair, wherein aligning further comprises;

determining which first language set pairs have a human translation word pair in the first language which differs from its corresponding correct translation first word pair in the first language; and

inserting into the confusion set database only those first language set pairs in which the human translation word pair in the first language differs from its corresponding correct translation word pair in the first language.

8. The method of claim 7, wherein using the processor to obtain the bilingual database having word pairs in the first and second languages includes:

obtaining a word and sentence aligned bilingual corpus.

9. The method of claim 7, wherein using the processor to obtain the bilingual database having word pairs in the first and second languages includes:

obtaining a word aligned bilingual dictionary.

10. The method of claim 7, wherein using the processor to obtain the human translation word pairs in the first language corresponding to each of the plurality of word pairs in the second language in the bilingual database further comprises:

performing human translation of each of the plurality of word pairs in the second language in the bilingual database into the human translation word pairs in the first language.