{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T19:22:12Z","timestamp":1771701732199,"version":"3.50.1"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2006,9,9]],"date-time":"2006-09-09T00:00:00Z","timestamp":1157760000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2006,9,9]],"date-time":"2006-09-09T00:00:00Z","timestamp":1157760000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Inf Retrieval"],"published-print":{"date-parts":[[2007,1]]},"DOI":"10.1007\/s10791-006-9001-9","type":"journal-article","created":{"date-parts":[[2006,9,8]],"date-time":"2006-09-08T20:34:06Z","timestamp":1157747646000},"page":"1-33","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":65,"title":["Lightweight natural language text compression"],"prefix":"10.1007","volume":"10","author":[{"given":"Nieves R.","family":"Brisaboa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio","family":"Fari\u00f1a","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gonzalo","family":"Navarro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos\u00e9 R.","family":"Param\u00e1","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2006,9,9]]},"reference":[{"key":"9001_CR1","doi-asserted-by":"crossref","unstructured":"Allauzen, C., Crochemore, M., & Raffinot, M. (1999). Factor oracle: a new structure for pattern matching. SOFSEM, LNCS 1725 (pp. 295\u2013310).","DOI":"10.1007\/3-540-47849-3_18"},{"key":"9001_CR2","doi-asserted-by":"crossref","unstructured":"Baeza-Yates, R., & Navarro, G. (2004). Recent advances in applied probability. In R. Baeza-Yates, J. Glaz, H. Gzyl, J. Husler & J. Palacios (Eds.), Modeling text databases (pp. 1\u201325). Springer.","DOI":"10.1007\/0-387-23394-6_1"},{"key":"9001_CR3","unstructured":"Baeza-Yates, R., & Ribeiro-Neto, B. (1999). Modern information retrieval. Addison-Wesley Longman."},{"key":"9001_CR4","unstructured":"Bell, T. C., Cleary, J. G., & Witten, I. H. (1990). Text compression. Prentice Hall."},{"issue":"10","key":"9001_CR5","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1145\/359842.359859","volume":"20","author":"R. S. Boyer","year":"1977","unstructured":"Boyer, R. S., & Moore, J. S. (1977). A fast string searching algorithm. Communications of the ACM, 20(10), 762\u2013772.","journal-title":"Communications of the ACM"},{"key":"9001_CR6","doi-asserted-by":"crossref","unstructured":"Brisaboa, N., Fari\u00f1a, A., Navarro, G., & Esteller, M. (2003a). (s,c)-densecoding: an optimized compression code for natural language text databases. In Proceedings of the 10th International Symposium on String Processing and Information Retrieval (SPIRE'03) (pp. 122\u2013136). LNCS 2857, Springer-Verlag.","DOI":"10.1007\/978-3-540-39984-1_10"},{"key":"9001_CR7","doi-asserted-by":"crossref","unstructured":"Brisaboa, N., Fari\u00f1a, A., Navarro, G., & Param\u00e1, J. (2004). Simple, fast, and efficient natural language adaptive compression. In Proceedings of the 11th International Symposium on String Processing and Information Retrieval (SPIRE'04) (pp. 230\u2013241). LNCS 3246, Springer-Verlag.","DOI":"10.1007\/978-3-540-30213-1_34"},{"key":"9001_CR8","doi-asserted-by":"crossref","unstructured":"Brisaboa, N., Fari\u00f1a, A., Navarro, G., & Param\u00e1, J. (2005a). Compressing dynamic text collections via phrase-based coding. In Proceedings of the 9th European Conference on Research and Advanced Technology for Digital Libraries (ECDL'05) (pp. 462\u2013474). LNCS 3652, Springer-Verlag.","DOI":"10.1007\/11551362_41"},{"key":"9001_CR9","doi-asserted-by":"crossref","unstructured":"Brisaboa, N., Fari\u00f1a, A., Navarro, G., & Param\u00e1, J. (2005b). Efficiently decodable and searchable natural language adaptive compression. In Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'05) (pp. 234\u2013241). ACM Press.","DOI":"10.1145\/1076034.1076076"},{"key":"9001_CR10","doi-asserted-by":"crossref","unstructured":"Brisaboa, N., Iglesias, E. L., Navarro, G., & Param\u00e1, J. R. (2003b). An efficient compression code for text databases. In Proceedings of the 25th European Conference on IR Research (ECIR'03) (pp. 468\u2013481). LNCS 2633, Springer-Verlag.","DOI":"10.1007\/3-540-36618-0_33"},{"key":"9001_CR11","unstructured":"Burrows, M., & Wheeler, D. J. (1994). A block-sorting lossless data compression algorithm, Technical Report 124, Digital Equipment Corporation."},{"key":"9001_CR12","unstructured":"Carpinelli, J., Moffat, A., Neal, R., Salamonsen, W., Stuiver, L., Turpin, A., & Witten, I. (1999), Word, character, integer, and bit based compression using arithmetic coding. http:\/\/www.cs.mu.oz.au\/~alistair\/arith_coder\/"},{"key":"9001_CR13","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1109\/TIT.1975.1055349","volume":"21","author":"P. Elias","year":"1975","unstructured":"Elias, P. (1975). Universal codeword sets and the representation of the integers. IEEE Transactions on Information Theory, 21, 194\u2013203.","journal-title":"IEEE Transactions on Information Theory"},{"key":"9001_CR14","unstructured":"Fari\u00f1a, A. (2005). New compression codes for text databases, PhD thesis, Database Laboratory, University of A Coruna. http:\/\/coba.dc.fi.udc.es\/~fari\/phd\/"},{"key":"9001_CR15","doi-asserted-by":"crossref","unstructured":"Fraenkel, & Klein. (1996). Robust universal complete codes for transmission and compression. Discrete Applied Mathematics and Combinatorial Operations Research and Computer Science, 64, 31\u201355.","DOI":"10.1016\/0166-218X(93)00116-H"},{"issue":"2","key":"9001_CR16","first-page":"23","volume":"12","author":"P Gage","year":"1994","unstructured":"Gage, P. (1994). A new algorithm for data compression. C Users Journal, 12(2), 23\u201338.","journal-title":"C Users Journal"},{"key":"9001_CR17","unstructured":"Heaps, H. S. (1978). Information retrieval: computational and theoretical aspects. New York: Academic Press."},{"issue":"6","key":"9001_CR18","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1002\/spe.4380100608","volume":"10","author":"R. N. Horspool","year":"1980","unstructured":"Horspool, R. N. (1980). Practical fast searching in strings. Software Practice and Experience, 10(6), 501\u2013506.","journal-title":"Software Practice and Experience"},{"key":"9001_CR19","doi-asserted-by":"crossref","unstructured":"Huffman, D. A. (1952). A method for the construction of minimum redundancy codes. In Proceedings of the Institute of Electronics and Radio Engineers (IRE), 40(9), 1098\u20131101.","DOI":"10.1109\/JRPROC.1952.273898"},{"issue":"4","key":"9001_CR20","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1016\/j.ipm.2003.08.008","volume":"41","author":"S. T. Klein","year":"2005","unstructured":"Klein, S. T., & Shapira, D. (2005). Pattern matching in Huffman encoded texts. Information Processing and Management, 41(4), 829\u2013841.","journal-title":"Information Processing and Management"},{"issue":"5","key":"9001_CR21","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1109\/TIT.1981.1056387","volume":"27","author":"K. B. Lakshmanan","year":"1981","unstructured":"Lakshmanan, K. B. (1981). On universal codeword sets. IEEE Transactions on Information Theory, 27(5), 659\u2013662.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"2","key":"9001_CR22","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1145\/248625.248639","volume":"15","author":"U. Manber","year":"1997","unstructured":"Manber, U. (1997). A text compression scheme that allows fast searching directly in the compressed file. ACM Transactions on Information Systems, 15(2), 124\u2013136.","journal-title":"ACM Transactions on Information Systems"},{"key":"9001_CR23","unstructured":"Manber, U., & Wu, S. (1994). GLIMPSE: A tool to search through entire file systems. In Proc. of the Winter 1994 USENIX Technical Conference (pp. 23\u201332)."},{"key":"9001_CR24","unstructured":"Mandelbrot, B. (1953). An information theory of the statistical structure of language. In W. Jackson (Ed.), Communication theory (pp. 486\u2013504). Academic Press N.Y."},{"issue":"9","key":"9001_CR25","first-page":"2638","volume":"39","author":"M. Miyazaki","year":"1998","unstructured":"Miyazaki, M., Fukamachi, S., Takeda, M., & Shinohara, T. (1998). Speeding up the pattern matching machine for compressed texts. Transactions of Information Processing Society of Japan, 39(9), 2638\u20132648.","journal-title":"Transactions of Information Processing Society of Japan"},{"key":"9001_CR26","doi-asserted-by":"crossref","unstructured":"Moffat, A. (1989). Word-based text compression. Software\u2014Practice and Experience, 19(2), 185\u2013198.","DOI":"10.1002\/spe.4380190207"},{"key":"9001_CR27","doi-asserted-by":"crossref","unstructured":"Moffat, A., & Katajainen, J. (1995). In-place calculation of minimum-redundancy codes. In Proceedings of the 4th International Workshop on Algorithms and Data Structures (WADS'95) (pp. 393\u2013402). LNCS 955, Springer.","DOI":"10.1007\/3-540-60220-8_79"},{"key":"9001_CR28","doi-asserted-by":"crossref","unstructured":"Moffat, A., & Turpin (1996). On the implementation of minimum redundancy prefix codes. IEEE Transactions on Communications, 45, 170\u2013179.","DOI":"10.1109\/26.634683"},{"key":"9001_CR29","doi-asserted-by":"crossref","unstructured":"Moura, E., Navarro, G., Ziviani, N., & Baeza-Yates, R. (1998). Fast searching on compressed text allowing errors. In Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'98) (pp. 298\u2013306). ACM Press.","DOI":"10.1145\/290941.291013"},{"issue":"2","key":"9001_CR30","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1145\/348751.348754","volume":"18","author":"E. Moura","year":"2000","unstructured":"Moura, E., Navarro, G., Ziviani, N., & Baeza-Yates, R. (2000). Fast and flexible word searching on compressed text., ACM Transactions on Information Systems, 18(2), 113\u2013139.","journal-title":"ACM Transactions on Information Systems"},{"issue":"5","key":"9001_CR31","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1016\/j.ipl.2005.07.004","volume":"96","author":"G. Navarro","year":"2006","unstructured":"Navarro, G., & Brisaboa, N. (2006). New bounds on D-ary optimal codes. Information Processing Letters, 96(5), 178\u2013184.","journal-title":"Information Processing Letters"},{"issue":"1","key":"9001_CR32","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1023\/A:1009934302807","volume":"3","author":"G. Navarro","year":"2000","unstructured":"Navarro, G., Moura, E., Neubert, M., Ziviani, N., & Baeza-Yates, R. (2000). Adding compression to block addressing inverted indexes. Information Retrieval, 3(1), 49\u201377.","journal-title":"Information Retrieval"},{"key":"9001_CR33","doi-asserted-by":"crossref","unstructured":"Navarro, G., & Raffinot, M. (2002). Flexible pattern matching in strings\u2014practical on-line search algorithms for texts and biological sequences. Cambridge University Press.","DOI":"10.1017\/CBO9781316135228"},{"key":"9001_CR34","doi-asserted-by":"crossref","unstructured":"Navarro, & Tarhio, J. (2000). Boyer-Moore string matching over Ziv-Lempel compressed text. In Proceedings of the 11th Annual Symposium on Combinatorial Pattern Matching, number 1848 in Lecture Notes in Computer Science (pp. 166\u2013180). Springer-Verlag, Berlin, Montreal, Canada.","DOI":"10.1007\/3-540-45123-4_16"},{"key":"9001_CR35","doi-asserted-by":"crossref","unstructured":"Navarro, & Tarhio, J. (2005). LZgrep: A Boyer-Moore string matching tool for Ziv-Lempel compressed text. Software Practice and Experience (SPE), 35(12), 1107\u20131130.","DOI":"10.1002\/spe.663"},{"key":"9001_CR36","doi-asserted-by":"crossref","unstructured":"Rautio, J., Tanninen, J., & Tarhio, J. (2002). String matching with stopper encoding and code splitting. In Proceedings of the 13th Annual Symposium on Combinatorial Pattern Matching (CPM 2002) (pp. 42\u201352). LNCS 2373, Springer.","DOI":"10.1007\/3-540-45452-7_5"},{"key":"9001_CR37","doi-asserted-by":"crossref","unstructured":"Savari, S. A., & Szpankowski, W. (2002) On the analysis of variable-to-variable length codes. In Proceedings of 2002 IEEE International Symposium on Information Theory (ISIT'02), (p. 176). See also http:\/\/citeseer.ist.psu.edu\/616808.html","DOI":"10.1109\/ISIT.2002.1023448"},{"key":"9001_CR38","doi-asserted-by":"crossref","unstructured":"Shibata, Y., Matsumoto, T., Takeda, M., Shinohara, A., & Arikawa, S. (2000). A Boyer-Moore type algorithm for compressed pattern matching. In Proceedings of the 11th Annual Symposium on Combinatorial Pattern Matching (CPM'00) (pp. 181\u2013194). LNCS 1848, Springer\u2013Verlag.","DOI":"10.1007\/3-540-45123-4_17"},{"issue":"3","key":"9001_CR39","first-page":"370","volume":"42","author":"M. Takeda","year":"2001","unstructured":"Takeda, M., Shibata, Y., Matsumoto, T., Kida, T., Shinohara, A., Fukamachi, S., Shinohara, T., & Arikawa, S. (2001). Speeding up string pattern matching by text compression: the dawn of a new era. Transactions of Information Processing Society of Japan, 42(3), 370\u2013384.","journal-title":"Transactions of Information Processing Society of Japan"},{"key":"9001_CR40","unstructured":"Turpin, A., & Moffat, A. (1997). Fast file search using text compression. In Proceedings of the 20th Australian Computer Science Conference (pp. 1\u20138)."},{"key":"9001_CR41","unstructured":"Wan, R. (2003). Browsing and searching compressed documents. PhD thesis, Department of Computer Science and Software Engineering, University of Melbourne, Australia. http:\/\/eprints. unimelb.edu.au\/archive\/00000484\/"},{"key":"9001_CR42","unstructured":"Witten, I. H., Moffat, A., & Bell, T. C. (1999). Managing gigabytes: compressing and indexing documents and images. Morgan Kaufmann Publishers, USA."},{"key":"9001_CR43","unstructured":"Wu, S., & Manber, U. (1992a). Agrep\u2014a fast approximate pattern-matching tool. In Proceedings USENIX Winter 1992 Technical Conference (pp. 153\u2013162). San Francisco, CA."},{"issue":"10","key":"9001_CR44","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1145\/135239.135244","volume":"35","author":"S. Wu","year":"1992b","unstructured":"Wu, S., & Manber, U. (1992b). Fast text searching allowing errors, Communications of the ACM, 35(10), 83\u201391.","journal-title":"Communications of the ACM"},{"key":"9001_CR45","unstructured":"Zipf, G. K. (1949). Human behavior and the principle of least Effort. Addison-Wesley."},{"issue":"3","key":"9001_CR46","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1109\/TIT.1977.1055714","volume":"23","author":"J. Ziv","year":"1977","unstructured":"Ziv, J., & Lempel, A. (1977). A universal algorithm for sequential data compression. IEEE Transactions on Information Theory, 23(3), 337\u2013343.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"5","key":"9001_CR47","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1109\/TIT.1978.1055934","volume":"24","author":"J. Ziv","year":"1978","unstructured":"Ziv, J., & Lempel, A. (1978). Compression of individual sequences via variable-rate coding. IEEE Transactions on Information Theory, 24(5), 530\u2013536.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"11","key":"9001_CR48","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/2.881693","volume":"33","author":"N. Ziviani","year":"2000","unstructured":"Ziviani, N., Moura, E., Navarro, G., & Baeza-Yates, R. (2000). Compression: a key for next-generation text retrieval systems. IEEE Computer, 33(11), 37\u201344.","journal-title":"IEEE Computer"}],"container-title":["Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-006-9001-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10791-006-9001-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-006-9001-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-006-9001-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T20:09:40Z","timestamp":1736539780000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10791-006-9001-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,9,9]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2007,1]]}},"alternative-id":["9001"],"URL":"https:\/\/doi.org\/10.1007\/s10791-006-9001-9","relation":{},"ISSN":["1386-4564","1573-7659"],"issn-type":[{"value":"1386-4564","type":"print"},{"value":"1573-7659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006,9,9]]},"assertion":[{"value":"6 September 2005","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 March 2006","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2006","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}