{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T21:04:04Z","timestamp":1725483844274},"publisher-location":"Berlin, Heidelberg","reference-count":24,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540709381"},{"type":"electronic","value":"9783540709398"}],"license":[{"start":{"date-parts":[[2007,1,1]],"date-time":"2007-01-01T00:00:00Z","timestamp":1167609600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007]]},"DOI":"10.1007\/978-3-540-70939-8_4","type":"book-chapter","created":{"date-parts":[[2007,5,19]],"date-time":"2007-05-19T07:15:01Z","timestamp":1179558901000},"page":"35-49","source":"Crossref","is-referenced-by-count":3,"title":["Conquering Language: Using NLP on a Massive Scale to Build High Dimensional Language Models from the Web"],"prefix":"10.1007","author":[{"given":"Gregory","family":"Grefenstette","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"unstructured":"Grefenstette, G., Nioche, J.: Estimation of English and non-English language use on the WWW. In: Proceedings of RIAO (2000)","key":"4_CR1"},{"key":"4_CR2","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1145\/1142473.1142504","volume-title":"Proceedings of the 2006 ACM SIGMOD international Conference on Management of Data, SIGMOD \u201906","author":"P.G. Ipeirotis","year":"2006","unstructured":"Ipeirotis, P.G., Agichtein, E., Jain, P., Gravano, L.: To search or to crawl?: towards a query optimizer for text-centric tasks. In: Proceedings of the 2006 ACM SIGMOD international Conference on Management of Data, SIGMOD \u201906, Chicago, IL, USA, June 27 - 29, pp. 265\u2013276. ACM Press, New York (2006)"},{"unstructured":"Nemeth, L., Tron, V., Halacsy, P., Kornai, A., Rung, A., Szakadat, I.: Leveraging the open source ispell codebase for minority language analysis. In: First Steps in Language Documentation for Minority Languages: Computational Linguistic Tools for Morphology, Lexicon and Corpus Compilation, Proceedings of the SALTMIL Workshop at LREC, pp. 56\u201359 (2004)","key":"4_CR3"},{"key":"4_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1007\/978-3-540-30222-3_16","volume-title":"Comparative Evaluation of Multilingual Information Access Systems","author":"R. Besan\u00e7on","year":"2004","unstructured":"Besan\u00e7on, R., de Chalendar, G., Ferret, O., Fluhr, C., Mesnard, O., Naets, H.: Concept-Based Searching and Merging for Multilingual Information Retrieval: First Experiments at CLEF 2003. In: Peters, C., Gonzalo, J., Braschler, M., Kluck, M. (eds.) CLEF 2003. LNCS, vol.\u00a03237, pp. 174\u2013184. Springer, Heidelberg (2004)"},{"unstructured":"Cavnar, W.B., Trenkle, J.M.: N-gram based text categorization. In: Proceedings of SDAIR-94, 3rd Annual Symposium on Document Analysis and Information Retrieval, Las Vegas, NV, pp. 161\u2013175 (1994)","key":"4_CR5"},{"unstructured":"Grefenstette, G.: Comparing two language identification schemes. In: Proceedings of the Third International Conference on the Statistical Analysis of Textual Data (JADT\u201995), Rome, December 11-13, pp. 263\u2013268 (1995)","key":"4_CR6"},{"issue":"3","key":"4_CR7","doi-asserted-by":"publisher","first-page":"516","DOI":"10.3758\/BF03195598","volume":"36","author":"B. New","year":"2004","unstructured":"New, B., Pallier, C., Brysbaert, M., Fer, L.: Lexique 2: A New French Lexical Database. Behavior Research Methods, Instruments, & Computers\u00a036(3), 516\u2013524 (2004)","journal-title":"Behavior Research Methods, Instruments, & Computers"},{"doi-asserted-by":"crossref","unstructured":"Cunningham, H.: GATE: A Framework and Graphical Development Environment for Robust NLP Tools and Applications. In: Proc. 40th Anniversary Meeting Assoc. for Computational Linguistics (ACL 2002). Assoc. for Computational Linguistics, East Stroudsburg, Pa. (2002)","key":"4_CR8","DOI":"10.3115\/1073083.1073112"},{"doi-asserted-by":"crossref","unstructured":"Kikui, G-I.: Identifying the coding system and language of on-line documents on the internet. In: Proceedings of the 16th International Conference on Computational Linguistics (COLING) (1996)","key":"4_CR9","DOI":"10.3115\/993268.993282"},{"unstructured":"Berland, S., Grabar, N.: Assistance automatique pour l\u2019homog\u00e9n\u00e9isation d\u2019un corpus Web de sp\u00e9cialit\u00e9. In: Actes des 6\u00e8mes Journ\u00e9es internationales d\u2019analyse statistique des donn\u00e9es textuelles, JADT 2002, Saint-Malo (2002)","key":"4_CR10"},{"issue":"4","key":"4_CR11","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1023\/A:1019213109274","volume":"2","author":"A. Heydon","year":"1999","unstructured":"Heydon, A., Najork, M.: Mercator: A scalable, extensible Web crawler. World Wide Web\u00a02(4), 219\u2013229 (1999)","journal-title":"World Wide Web"},{"doi-asserted-by":"crossref","unstructured":"Sundheim, B.: Overview of results of the MUC-6 evaluation. In: Proceedings of Sixth Message Understanding Conference (MUC-6), Columbia, Maryland, November 6-8, pp. 13\u201332 (1995)","key":"4_CR12","DOI":"10.3115\/1072399.1072402"},{"issue":"1","key":"4_CR13","first-page":"22","volume":"16","author":"K.W. Church","year":"1990","unstructured":"Church, K.W., Hanks, P.: Word association norms, mutual information, and lexicography. Comput. Linguist.\u00a016(1), 22\u201329 (1990)","journal-title":"Comput. Linguist."},{"issue":"2","key":"4_CR14","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s007999900025","volume":"3","author":"D. Hiemstra","year":"2000","unstructured":"Hiemstra, D.: A probabilistic justification for using tf.idf term weighting in information retrieval. International Journal on Digital Libraries\u00a03(2), 131\u2013139 (2000)","journal-title":"International Journal on Digital Libraries"},{"issue":"1","key":"4_CR15","first-page":"103","volume":"19","author":"D. Hindle","year":"1993","unstructured":"Hindle, D., Rooth, M.: Structural ambiguity and lexical relations. Computational Linguistics\u00a019(1), 103\u2013120 (1993)","journal-title":"Computational Linguistics"},{"unstructured":"Merlo, P., Crocker, M.W., Berthouzoz, C.: Attaching multiple prepositional phrases: Generalized Backed-off Estimation. In: Cardie, C., Weischedel, R. (eds.) Proceedings of the second conference on Empirical Methods in Natural Language Processing, EMNLP-97, pp. 149\u2013155 (1997)","key":"4_CR16"},{"doi-asserted-by":"crossref","unstructured":"Nakov, P., Hearst, M.: Using the Web as an implicit training set: Application to structural ambiguity resolution. In: Proceedings of HLT-EMNLP, Vancouver, British Columbia, Canada, pp. 835\u2013842 (2005)","key":"4_CR17","DOI":"10.3115\/1220575.1220680"},{"unstructured":"Grefenstette, G.: The World Wide Web as a resource for example-based machine translation tasks. In: Proceedings of the ASLIB Conference on Translating and the Computer, London (1998)","key":"4_CR18"},{"unstructured":"Li, Y., Grefenstette, G.: Translating Chinese idiographic characters via corpus and web validation. In: CORIA\u20192005, Grenoble, France, March 9-11 (2005)","key":"4_CR19"},{"doi-asserted-by":"crossref","unstructured":"Qu, Y., Grefenstette, G.: Finding Ideographic Representations of Japanese Names Written in Latin Script via Language Identification and Corpus Validation. In: Proc. of ACL, pp. 184\u2013191 (2004)","key":"4_CR20","DOI":"10.3115\/1218955.1218979"},{"issue":"4","key":"4_CR21","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1145\/944012.944013","volume":"21","author":"P.D. Turney","year":"2003","unstructured":"Turney, P.D., Littman, M.L.: Measuring praise and criticism: Inference of semantic orientation from association. ACM Transactions on Information Systems (TOIS)\u00a021(4), 315\u2013346 (2003)","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"doi-asserted-by":"crossref","unstructured":"Grefenstette, G.: The Color of Things: Towards the automatic acquisition of information for a descriptive dictionary. Revue Fran\u00e7aise de Linguisitque Appliqu\u00e9e, vol. X-2 1386-1204, 83-94 (2005)","key":"4_CR22","DOI":"10.3917\/rfla.102.94"},{"issue":"2","key":"4_CR23","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1145\/1046456.1046460","volume":"6","author":"P. Cimiano","year":"2004","unstructured":"Cimiano, P., Staab, S.: Learning by googling. ACM SIGKDD Explorations Newsletter\u00a06(2), 24\u201333 (2004)","journal-title":"ACM SIGKDD Explorations Newsletter"},{"unstructured":"Kilgarriff, A.: Linguistic search engine. In: Simov, K. (ed.) Shallow Processing of Large Corpora: Workshop Held in Association with Corpus Linguistics 2003, Lancaster, England (2003)","key":"4_CR24"}],"container-title":["Lecture Notes in Computer Science","Computational Linguistics and Intelligent Text Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-70939-8_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T18:32:36Z","timestamp":1683829956000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-70939-8_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"ISBN":["9783540709381","9783540709398"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-70939-8_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2007]]}}}