Demographic based classification for local word wheeling/web search

Illllllllllllllllllllllllllllllllllllllllllllllllll

US007778837B2

(12;

United States Patent

Thiesson et al.

(io) Patent No.: (45) Date of Patent:

US 7,778,837 B2 Aug. 17, 2010

(54) DEMOGRAPHIC BASED CLASSIFICATION FOR LOCAL WORD WHEELING/WEB SEARCH

(75) Inventors: Bo Thiesson, Woodinville, WA (US);

Kenneth W. Church, Seattle, WA (US)

(73) Assignee: Microsoft Corporation, Redmond, WA (US)

( * ) Notice: Subject to any disclaimer, the term of this patent is extended or adjusted under 35 U.S.C. 154(b) by 843 days.

(21) Appl.No.: 11/565,231

(22) Filed: Nov. 30, 2006

(65) Prior Publication Data

US 2007/0255552 Al Nov. 1, 2007

Related U.S. Application Data

(60) Provisional application No. 60/746,134, filed on May 1,2006.

(51) Int. CI.

G10L 21/00 (2006.01)

(52) U.S. CI 704/278; 704/7; 704/9;

704/246; 704/251

(58) Field of Classification Search None

See application file for complete search history.

(56) References Cited

U.S. PATENT DOCUMENTS

Systems and methods that create a classification of sentences in a language, and further construct associated local versions of language models, based on geographical location and/or other demographic criteria—wherein such local language models can be of different levels of granularity according to chosen demographic criteria. The subject innovation employs a classification encoder component that forms a classification (e.g. a tree structure) of sentences, and a local language models encoder component, which employs the classification of sentences in order to construct the localized language models. A decoder component can subsequently enable local word wheeling and/or local web search by blending k-best answers from local language models of varying demographic granularity that match users demographics. Hence, k-best matches for input data by users in one demographic locality can be different from k-best matches for the same input by other users in another locality.

16 Claims, 10 Drawing Sheets

U.S. PATENT DOCUMENTS

2003/0061027 Al 3/2003 Weiseetal.

2003/0212702 Al * 11/2003 Campos et al 707/102

2004/0201607 Al 10/2004 Mulveyetal.

2004/0260534 Al 12/2004 Paketal.

2006/0085392 Al 4/2006 Wangetal.

2007/0147269 Al * 6/2007 Ettle et al 370/254

OTHER PUBLICATIONS

Lee Wang, et al. Detecting dominant locations from search queries,
SIGIR '05, Aug. 15-19, 2005, Salvador, Brazil.
JunyanDing, etal. Computing geographical scopes of web resources,
Proceedings of the 26fh VLDB Conference, Cairo, Egypt, 2000.
J. L. Bentley. Multidimensional binary search trees used for associa-
tive searching, Commun. ACM, 18:9, pp. 509-517, 1975.
S.L. Dumais, etal. Stuff I've Seen: A system for personal information
retrieval and re-use, SIGIR, 2003.

M. D. Mcllroy. Development of a spelling list, IEEE Lrans. on Communications 30, pp. 91-99, 1982.

M. Mohri, et al. Weighted Finite-State Lransducers in Speech Recognition. Computer Speech and Language, 16(1), pp. 69-88, 2002. Using the Word Wheel, Technical Tips, http://www.isys-search.com/ support/techtips/wordwheel.html, last accessed Jun. 23, 2005. MSN Desktop Search (beta), http://www.pcmag.com/article2/ 0,1759,1771841,00.asp, last accessed Jun. 23, 2005. F. Jelinek. Statistical Methods for Speech Recognition, pp. 60-67, 1997.

I. H. Witten, et al. Managing Gigabytes: Compressing and Indexing Documents and Images, by Morgan Kaufmann Publishing, San Francisco, 1999, pt. 1, 65 pages, (front cover-36).

I. H. Witten, et al. Managing Gigabytes: Compressing and Indexing Documents and Images, by Morgan Kaufmann Publishing, San Francisco, 1999, pt. 2, 65 pages, (37-101).

I. H. Witten, al. et al. Managing Gigabytes: Compressing and Indexing Documents and Images, by Morgan Kaufmann Publishing, San Francisco, 1999, pt. 3, 65 pages, (102-166).

I. H. Witten, al. et al Managing Gigabytes: Compressing and Indexing Documents and Images, by Morgan Kaufmann Publishing, San Francisco, 1999, pt. 4, 55 pages, (167-221).

I. H. Witten, al. et al Managing Gigabytes: Compressing and Indexing Documents and Images, by Morgan Kaufmann Publishing, San Francisco, 1999, pt. 5, 48 pages, (222-270).

I. H. Witten, et al. Managing Gigabytes: Compressing and Indexing Documents and Images, by Morgan Kaufmann Publishing, San Francisco, 1999, pt. 6, 58 pages, (271-328).

I. H. Witten, et al. Managing Gigabytes: Compressing and Indexing Documents and Images, by Morgan Kaufmann Publishing, San Francisco, 1999, pt. 7, 60 pages, (329-388).

I. H. Witten, et al. Managing Gigabytes: Compressing and Indexing Documents and Images, by Morgan Kaufmann Publishing, San Francisco, 1999, pt. 8, 65 pages, (389-452).

I. H. Witten, et al. Managing Gigabytes: Compressing and Indexing Documents and Images, by Morgan Kaufmann Publishing, San Francisco, 1999, pt. 9, 67 pages, (453-back cover).

* cited by examiner