{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T09:02:29Z","timestamp":1743152549981,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":21,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642003813"},{"type":"electronic","value":"9783642003820"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"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":[[2009]]},"DOI":"10.1007\/978-3-642-00382-0_5","type":"book-chapter","created":{"date-parts":[[2009,2,16]],"date-time":"2009-02-16T12:17:13Z","timestamp":1234786633000},"page":"53-71","source":"Crossref","is-referenced-by-count":2,"title":["Substring Statistics"],"prefix":"10.1007","author":[{"given":"Kyoji","family":"Umemura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenneth","family":"Church","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"5_CR1","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1037\/h0031564","volume":"90","author":"D. Meyer","year":"1971","unstructured":"Meyer, D., Schvaneveldt, R.: Facilitation in recognizing pairs of words: Evidence of a dependence between retrieval operations. Journal of Experimental Psychology\u00a090, 227\u2013234 (1971)","journal-title":"Journal of Experimental Psychology"},{"issue":"1","key":"5_CR2","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1108\/eb026526","volume":"28","author":"K.S. Jones","year":"1972","unstructured":"Jones, K.S.: A statistical interpretation of term specificity and its application in retrieval. Journal of Documentation\u00a028(1), 11\u201321 (1972)","journal-title":"Journal of Documentation"},{"key":"5_CR3","unstructured":"Prince, E.: Toward a taxonomy of given-new information. In: Cole, P. (ed.), pp. 236\u2013256. Academic Press, New York (1981)"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Davis, J.R., Hirschberg, J.: Meeting of the Association for Computational Linguistics, 187\u2013193 (1988)","DOI":"10.3115\/982023.982046"},{"key":"5_CR5","volume-title":"Automatic text processing","author":"G. Salton","year":"1988","unstructured":"Salton, G.: Automatic text processing. Addison-Wesley Longman Publishing Co., Inc., Amsterdam (1988)"},{"key":"5_CR6","first-page":"187","volume-title":"ACM Proceedings of the 1977 Annual Conference","author":"G. Steele","year":"1988","unstructured":"Steele, G.: Debunking the \u201cexpensive procedure call\u201d myth or, procedure call implementations considered harmful or, LAMBDA: The Ultimate GOTO. In: ACM Proceedings of the 1977 Annual Conference, pp. 187\u2013193. ACM Press, New York (1988)"},{"key":"5_CR7","volume-title":"Text Compression","author":"T. Bell","year":"1990","unstructured":"Bell, T., Cleary, J., Witten, I.: Text Compression. Prentice Hall, Englewood Cliffs (1990)"},{"key":"5_CR8","volume-title":"Statistical Language Learning","author":"E. Charniak","year":"1993","unstructured":"Charniak, E.: Statistical Language Learning. MIT Press, Cambridge (1993)"},{"issue":"5","key":"5_CR9","doi-asserted-by":"publisher","first-page":"935","DOI":"10.1137\/0222058","volume":"22","author":"U. Manber","year":"1993","unstructured":"Manber, U., Myers, G.: Suffix arrays: a new method for on-line string searches. SIAM J. Comput.\u00a022(5), 935\u2013948 (1993)","journal-title":"SIAM J. Comput."},{"key":"5_CR10","unstructured":"Harman, D., Liberman, M.: TIPSTER, LDC, vol.\u00a01 (1993), http:\/\/www.ldc.upenn.edu"},{"issue":"8-3","key":"5_CR11","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1016\/S0169-7552(97)00031-7","volume":"29","author":"A.Z. Broder","year":"1997","unstructured":"Broder, A.Z., Glassman, S.C., Manasse, M.S., Zweig, G.: Syntactic clustering of the Web. Comput. Netw. ISDN Syst.\u00a029(8-3), 1157\u20131166 (1997)","journal-title":"Comput. Netw. ISDN Syst."},{"key":"5_CR12","volume-title":"Managing gigabytes: compressing and indexing documents and images","author":"I. Witten","year":"1999","unstructured":"Witten, I., Moffat, A., Bell, T.: Managing gigabytes: compressing and indexing documents and images. Van Nostrand Reinhold, New York (1999)"},{"key":"5_CR13","volume-title":"Statistical Methods for Speech Recognition","author":"F. Jelinek","year":"1999","unstructured":"Jelinek, F.: Statistical Methods for Speech Recognition. MIT Press, Cambridge (1999)"},{"key":"5_CR14","volume-title":"Foundations of Statistical Natural Language Processing","author":"C.D. Manning","year":"1999","unstructured":"Manning, C.D., Sch\u00fctze, H.: Foundations of Statistical Natural Language Processing. MIT Press, Cambridge (1999)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Church, K.W.: Empirical Estimates of Adaptation: The chance of Two Noriegas is closer to p\/2 than p 2. In: Coling (2000)","DOI":"10.3115\/990820.990847"},{"key":"5_CR16","volume-title":"Speech and Language Processing","author":"D. Jurafsky","year":"2000","unstructured":"Jurafsky, D., Martin, J.H.: Speech and Language Processing. Prentice Hall, Upper Saddle River (2000)"},{"key":"5_CR17","volume-title":"Spoken Language Processing","author":"X. Huang","year":"2001","unstructured":"Huang, X., Acero, A., Hon, H.-W.: Spoken Language Processing. Prentice Hall, Upper Saddle River (2001)"},{"key":"5_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-010-0844-0","volume-title":"Word Frequency Distributions","author":"R.H. Baayen","year":"2001","unstructured":"Baayen, R.H.: Word Frequency Distributions. Kluwer Academic Publishers, Dordrecht (2001)"},{"issue":"1","key":"5_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/089120101300346787","volume":"27","author":"M. Yamamoto","year":"2001","unstructured":"Yamamoto, M., Church, K.: Using suffix arrays to compute term frequency and document frequency for all substrings in a corpus. Computational Linguistics\u00a027(1), 1\u201330 (2001)","journal-title":"Computational Linguistics"},{"issue":"1","key":"5_CR20","first-page":"411","volume":"1","author":"Y. Xu","year":"2006","unstructured":"Xu, Y., Umemura, K.: Improvements of Katz K Mixture Model. Information and Media Technologies\u00a01(1), 411\u2013435 (2006)","journal-title":"Information and Media Technologies"},{"key":"5_CR21","unstructured":"Umemura, K.: www.cicling.org\/2009\/Umemura-Church\/"}],"container-title":["Lecture Notes in Computer Science","Computational Linguistics and Intelligent Text Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-00382-0_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T18:56:36Z","timestamp":1738954596000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-00382-0_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642003813","9783642003820"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-00382-0_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}