{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T22:11:14Z","timestamp":1765231874601,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2010,4,26]],"date-time":"2010-04-26T00:00:00Z","timestamp":1272240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2010,4,26]]},"DOI":"10.1145\/1772690.1772737","type":"proceedings-article","created":{"date-parts":[[2010,4,27]],"date-time":"2010-04-27T12:45:48Z","timestamp":1272372348000},"page":"451-460","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":32,"title":["Exploring web scale language models for search query processing"],"prefix":"10.1145","author":[{"given":"Jian","family":"Huang","sequence":"first","affiliation":[{"name":"Pennsylvania State University, University Park, PA, USA"}]},{"given":"Jianfeng","family":"Gao","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, WA, USA"}]},{"given":"Jiangbo","family":"Miao","sequence":"additional","affiliation":[{"name":"Facebook, Palo Alto, CA, USA"}]},{"given":"Xiaolong","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, WA, USA"}]},{"given":"Kuansan","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, WA, USA"}]},{"given":"Fritz","family":"Behr","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"given":"C. Lee","family":"Giles","sequence":"additional","affiliation":[{"name":"Information Sciences and Technology, Pennsylvania State University, PA, USA"}]}],"member":"320","published-online":{"date-parts":[[2010,4,26]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Hitwise 2009 press releases 2009.  Hitwise 2009 press releases 2009."},{"volume-title":"September","year":"2003","key":"e_1_3_2_1_2_1","unstructured":"Special issue on web as corpus. Computational Linguistics, 29(3) , September 2003 . Special issue on web as corpus. Computational Linguistics, 29(3), September 2003."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148177"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073012.1073017"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/1613715.1613848"},{"key":"e_1_3_2_1_6_1","first-page":"1507","volume-title":"Proceedings of the 21st International Joint Conference on Artificial Intelligence (IJCAI)","author":"Bergsma S.","year":"2009","unstructured":"S. Bergsma , D. Lin , and R. Goebel . Web-scale n-gram models for lexical disambiguation . In Proceedings of the 21st International Joint Conference on Artificial Intelligence (IJCAI) , pages 1507 -- 1512 , 2009 . S. Bergsma, D. Lin, and R. Goebel. Web-scale n-gram models for lexical disambiguation. In Proceedings of the 21st International Joint Conference on Artificial Intelligence (IJCAI), pages 1507--1512, 2009."},{"key":"e_1_3_2_1_7_1","first-page":"819","volume-title":"Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing (EMNLP) and Computational Natural Language Learning (CoNLL)","author":"Bergsma S.","year":"2007","unstructured":"S. Bergsma and Q. I. Wang . Learning noun phrase query segmentation . In Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing (EMNLP) and Computational Natural Language Learning (CoNLL) , pages 819 -- 826 , 2007 . S. Bergsma and Q. I. Wang. Learning noun phrase query segmentation. In Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing (EMNLP) and Computational Natural Language Learning (CoNLL), pages 819--826, 2007."},{"key":"e_1_3_2_1_8_1","volume-title":"Google Research","author":"Brants T.","year":"2006","unstructured":"T. Brants and A. Franz . Web 1T 5-gram corpus version 1.1. Technical report , Google Research , 2006 . T. Brants and A. Franz. Web 1T 5-gram corpus version 1.1. Technical report, Google Research, 2006."},{"key":"e_1_3_2_1_9_1","first-page":"858","volume-title":"Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing (EMNLP) and Computational Natural Language Learning (CoNLL)","author":"Brants T.","year":"2007","unstructured":"T. Brants , A. C. Popat , P. Xu , F. J. Och , and J. Dean . Large language models in machine translation . In Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing (EMNLP) and Computational Natural Language Learning (CoNLL) , pages 858 -- 867 , 2007 . T. Brants, A. C. Popat, P. Xu, F. J. Och, and J. Dean. Large language models in machine translation. In Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing (EMNLP) and Computational Natural Language Learning (CoNLL), pages 858--867, 2007."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1999.0128"},{"key":"e_1_3_2_1_11_1","first-page":"199","volume-title":"Proceedings of EMNLP and CoNLL","author":"Church K.","year":"2007","unstructured":"K. Church , T. Hard , and J. Gao . Compressing trigram language models with Golomb coding . In Proceedings of EMNLP and CoNLL , pages 199 -- 207 , 2007 . K. Church, T. Hard, and J. Gao. Compressing trigram language models with Golomb coding. In Proceedings of EMNLP and CoNLL, pages 199--207, 2007."},{"key":"e_1_3_2_1_12_1","first-page":"293","volume-title":"EMNLP","author":"Cucerzan S.","year":"2004","unstructured":"S. Cucerzan and E. Brill . Spelling correction as an iterative process that exploits the collective knowledge of web users . In EMNLP , pages 293 -- 300 , 2004 . S. Cucerzan and E. Brill. Spelling correction as an iterative process that exploits the collective knowledge of web users. In EMNLP, pages 293--300, 2004."},{"key":"e_1_3_2_1_13_1","volume-title":"Proc. of IJCNLP","author":"Gamon M.","year":"2008","unstructured":"M. Gamon , J. Gao , C. Brockett , A. Klementiev , W. Dolan , D. Belenko , and L. Vanderwende . Using contextual speller techniques and language modeling for ESL error correction . In Proc. of IJCNLP , 2008 . M. Gamon, J. Gao, C. Brockett, A. Klementiev, W. Dolan, D. Belenko, and L. Vanderwende. Using contextual speller techniques and language modeling for ESL error correction. In Proc. of IJCNLP, 2008."},{"issue":"1","key":"e_1_3_2_1_14_1","first-page":"27","article-title":"The use of clustering techniques for language modelling - application to Asian languages","volume":"6","author":"Gao J.","year":"2001","unstructured":"J. Gao , J. Goodman , and J. Miao . The use of clustering techniques for language modelling - application to Asian languages . Computational Linguistics and Chinese Language Processing , 6 ( 1 ): 27 -- 60 , 2001 . J. Gao, J. Goodman, and J. Miao. The use of clustering techniques for language modelling - application to Asian languages. Computational Linguistics and Chinese Language Processing, 6(1):27--60, 2001.","journal-title":"Computational Linguistics and Chinese Language Processing"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1571941.1572003"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.3115\/981863.981873"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2009.36"},{"key":"e_1_3_2_1_18_1","volume-title":"Spoken Language Processing: A Guide to Theory, Algorithm and System Development","author":"Huang X.","year":"2001","unstructured":"X. Huang , A. Acero , and H.-W. Hon . Spoken Language Processing: A Guide to Theory, Algorithm and System Development . Prentice Hall PTR , 2001 . X. Huang, A. Acero, and H.-W. Hon. Spoken Language Processing: A Guide to Theory, Algorithm and System Development. Prentice Hall PTR, 2001."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1135777.1135835"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1571941.1572038"},{"key":"e_1_3_2_1_22_1","first-page":"121","volume-title":"Proc. of Human Language Technologies - North American Chapter of the Association for Computational Linguistics (HLT-NAACL)","author":"Lapata M.","year":"2004","unstructured":"M. Lapata and F. Keller . The web as a baseline: Evaluating the performance of unsupervised web-based models for a range of NLP tasks . In Proc. of Human Language Technologies - North American Chapter of the Association for Computational Linguistics (HLT-NAACL) , pages 121 -- 128 , 2004 . M. Lapata and F. Keller. The web as a baseline: Evaluating the performance of unsupervised web-based models for a range of NLP tasks. In Proc. of Human Language Technologies - North American Chapter of the Association for Computational Linguistics (HLT-NAACL), pages 121--128, 2004."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.3115\/981658.981665"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/1706543.1706547"},{"key":"e_1_3_2_1_25_1","volume-title":"Microsoft Research","author":"Nguyen P.","year":"2007","unstructured":"P. Nguyen , J. Gao , and M. Mahajan . MSRLM: a scalable language modeling toolkit. Technical report TR-2007-144 , Microsoft Research , 2007 . P. Nguyen, J. Gao, and M. Mahajan. MSRLM: a scalable language modeling toolkit. Technical report TR-2007-144, Microsoft Research, 2007."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/1097-4571(2000)9999:9999%3C::AID-ASI1591%3E3.3.CO;2-I"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1645953.1646237"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1367497.1367545"},{"key":"e_1_3_2_1_29_1","first-page":"104","volume-title":"Proceedings of 10th Conference of the Pacific Association for Computational Linguistics (PACLING)","author":"Vadas D.","year":"2007","unstructured":"D. Vadas and J. R. Curran . Corpus statistics meet the noun compound: some empirical results . In Proceedings of 10th Conference of the Pacific Association for Computational Linguistics (PACLING) , pages 104 -- 112 , 2007 . D. Vadas and J. R. Curran. Corpus statistics meet the noun compound: some empirical results. In Proceedings of 10th Conference of the Pacific Association for Computational Linguistics (PACLING), pages 104--112, 2007."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960688"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/984321.984322"}],"event":{"name":"WWW '10: The 19th International World Wide Web Conference","acronym":"WWW '10","location":"Raleigh North Carolina USA"},"container-title":["Proceedings of the 19th international conference on World wide web"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1772690.1772737","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1772690.1772737","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T20:26:29Z","timestamp":1750278389000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1772690.1772737"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,4,26]]},"references-count":31,"alternative-id":["10.1145\/1772690.1772737","10.1145\/1772690"],"URL":"https:\/\/doi.org\/10.1145\/1772690.1772737","relation":{},"subject":[],"published":{"date-parts":[[2010,4,26]]},"assertion":[{"value":"2010-04-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}