{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T05:36:13Z","timestamp":1775280973473,"version":"3.50.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1-3","license":[{"start":{"date-parts":[[1999,2,1]],"date-time":"1999-02-01T00:00:00Z","timestamp":917827200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[1999,2,1]],"date-time":"1999-02-01T00:00:00Z","timestamp":917827200000},"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":["Machine Learning"],"published-print":{"date-parts":[[1999,2]]},"DOI":"10.1023\/a:1007541817488","type":"journal-article","created":{"date-parts":[[2002,12,22]],"date-time":"2002-12-22T05:04:10Z","timestamp":1040533450000},"page":"71-105","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":110,"title":["An Efficient, Probabilistically Sound Algorithm for Segmentation and Word Discovery"],"prefix":"10.1007","volume":"34","author":[{"given":"Michael R.","family":"Brent","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"197127_CR1","first-page":"117","volume-title":"Signal to syntax: Bootstrapping from speech to grammar in early acquisition","author":"R.N. Aslin","year":"1996","unstructured":"Aslin, R.N., Woodward, J.Z., LaMendola, N.P., & Bever, T.G. (1996). Models of word segmentation in fluent maternal speech to infants. In J.L. Morgan & K. Demuth (Eds.), Signal to syntax: Bootstrapping from speech to grammar in early acquisition (pp. 117\u2013134). Mahwah, NJ: Lawrence Erlbaum Associates."},{"key":"197127_CR2","doi-asserted-by":"crossref","unstructured":"Baayen, H. (1991). A stochastic process for word frequency distributions. Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, Berkeley, CA.","DOI":"10.3115\/981344.981379"},{"key":"197127_CR3","volume-title":"Children's language","author":"N. Bernstein-Ratner","year":"1987","unstructured":"Bernstein-Ratner, N. (1987). The phonology of parent child speech. In K. Nelson & A. van Kleeck (Eds.), Children's language (Vol. 6). Hillsdale, NJ: Erlbaum."},{"key":"197127_CR4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0010-0277(96)00779-2","volume":"61","author":"M.R. Brent","year":"1996","unstructured":"Brent, M.R. (1996). Advances in computational study of language acquisition. Cognition, 61, 1\u201338.","journal-title":"Cognition"},{"key":"197127_CR5","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1023\/A:1025032825951","volume":"26","author":"M.R. Brent","year":"1997","unstructured":"Brent, M.R. (1997). Toward a unified model of lexical acquisition and lexical access. Journal of Psycholinguistic Research, 26, 363\u2013375.","journal-title":"Journal of Psycholinguistic Research"},{"key":"197127_CR6","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/S0010-0277(96)00719-6","volume":"61","author":"M.R. Brent","year":"1996","unstructured":"Brent, M.R., & Cartwright, T.A. (1996). Distributional regularity and phonotactics are useful for segmentation. Cognition, 61, 93\u2013125.","journal-title":"Cognition"},{"key":"197127_CR7","volume-title":"Proceedings of the 16th Annual Meeting of the Cognitive Science Society","author":"T.A. Cartwright","year":"1994","unstructured":"Cartwright, T.A., & Brent, M.R. (1994). Segmenting speech without a lexicon: Evidence for a bootstrapping model of lexical acquisition. Proceedings of the 16th Annual Meeting of the Cognitive Science Society. Hillsdale, NJ: Erlbaum."},{"key":"197127_CR8","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/S0010-0277(96)00793-7","volume":"63","author":"T.A. Cartwright","year":"1997","unstructured":"Cartwright, T.A., & Brent, M.R. (1997). Syntactic categorization in early language acquisition: Formalizing the role of distributional analysis. Cognition, 63, 121\u2013170.","journal-title":"Cognition"},{"key":"197127_CR9","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1080\/016909698386528","volume":"13","author":"M.H. Christiansen","year":"1998","unstructured":"Christiansen, M.H., Allen, J., & Seidenberg, M. (1998). Learning to segment speech using multiple cues: A connectionist model. To appear in Language and Cognitive Processes, 13, 221\u2013268.","journal-title":"To appear in Language and Cognitive Processes"},{"key":"197127_CR10","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/0885-2308(91)90016-J","volume":"5","author":"K.W. Church","year":"1991","unstructured":"Church, K.W., & Gale, W.A. (1991). A comparison of the enhanced good-turing and deleted estimation methods for estimating probabilities of English bigrams. Computer Speech and Language, 5, 19\u201354.","journal-title":"Computer Speech and Language"},{"key":"197127_CR11","doi-asserted-by":"crossref","unstructured":"Dahan, D., & Brent, M.R. (1999). On the discovery of novelword-like units from utterances: An artificial-language study with implications for native-language acquisition. To appear in Journal of Experimental Psychology: General (in press).","DOI":"10.1037\/\/0096-3445.128.2.165"},{"key":"197127_CR12","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","volume":"14","author":"J.L. Elman","year":"1990","unstructured":"Elman, J.L. (1990). Finding structure in time. Cognitive Science, 14, 179\u2013211.","journal-title":"Cognitive Science"},{"key":"197127_CR13","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1163\/9789004653566_015","volume-title":"Corpus-based research into language","author":"W.A. Gale","year":"1994","unstructured":"Gale, W.A., & Church, K.W. (1994). What is wrong with adding one? In Nelleke Oostdijk & P. de Haan (Eds.), Corpus-based research into language (pp. 189\u2013198). Amsterdam: Rodopi."},{"key":"197127_CR14","volume-title":"Introduction to information theory and data comprestsion","author":"D. Hankerson","year":"1998","unstructured":"Hankerson, D., Harris, G.A., & Johnson, P.D., Jr. (1998). Introduction to information theory and data comprestsion. New York: CRC Press."},{"key":"197127_CR15","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1080\/00437956.1954.11659520","volume":"10","author":"Z.S. Harris","year":"1954","unstructured":"Harris, Z.S. (1954). Distributional structure. Word, 10, 146\u2013162.","journal-title":"Word"},{"key":"197127_CR16","volume-title":"Statistical methods for speech recognition","author":"F. Jelinek","year":"1997","unstructured":"Jelinek, F. (1997). Statistical methods for speech recognition. Cambridge: MIT Press."},{"key":"197127_CR17","unstructured":"Kraft, L.G. (1949). A device for quantizing, grouping and coding amplitude modulated pulses. Unpublished Master's thesis, Massachusetts Institute of Technology."},{"key":"197127_CR18","doi-asserted-by":"crossref","unstructured":"Li, M., & Vit\u00e1nyi, P.M.B. (1993). An introduction to Kolmogorov complexity and its applications.","DOI":"10.1007\/978-1-4757-3860-5"},{"key":"197127_CR19","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1017\/S0305000900006449","volume":"12","author":"B. MacWhinney","year":"1985","unstructured":"MacWhinney, B., & Snow, C. (1985). The child language data exchange system. Journal of Child Language, 12, 271\u2013296.","journal-title":"Journal of Child Language"},{"key":"197127_CR20","unstructured":"Mandelbrot, B. (1953). An informational theory of the statistical structure of language. In W. Jackson (Ed.), Communication theory. Butterworths."},{"key":"197127_CR21","unstructured":"de Marcken, C. (1995). The unsupervised acquisition of a lexicon from continuous speech. AI Memo No. 1558, Massachusetts Institute of Technology."},{"key":"197127_CR22","doi-asserted-by":"crossref","first-page":"311","DOI":"10.2307\/1419346","volume":"52","author":"G.A. Miller","year":"1957","unstructured":"Miller, G.A. (1957). Some effects of intermittent silence. The American Journal of Psychology, 52, 311\u2013314.","journal-title":"The American Journal of Psychology"},{"key":"197127_CR23","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1093\/comjnl\/40.2_and_3.103","volume":"40","author":"C.G. Nevill-Manning","year":"1997","unstructured":"Nevill-Manning, C.G., & Witten, I.H. (1997). Compression and explanation using hierarchical grammars. Computer Journal, 40, 103\u2013116.","journal-title":"Computer Journal"},{"key":"197127_CR24","unstructured":"Olivier, D.C. (1968). Stochastic grammars and language acquisition mechanisms. Unpublished doctoral dissertation, Harvard University."},{"key":"197127_CR25","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/0890-5401(89)90010-2","volume":"80","author":"J.R. Quinlan","year":"1989","unstructured":"Quinlan, J.R., & Rivest, R.L. (1989). Inferring decision trees using the minimum description length principle. Information and Computation, 80, 227\u2013248.","journal-title":"Information and Computation"},{"key":"197127_CR26","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1162\/neco.1993.5.2.289","volume":"5","author":"A.N. Redlich","year":"1993","unstructured":"Redlich, A.N. (1993). Redundancy reduction as a strategy for unsupervised learning. Neural Computation, 5, 289\u2013304.","journal-title":"Neural Computation"},{"key":"197127_CR27","volume-title":"Stochastic complexity in statistical inquiry","author":"J. Rissanen","year":"1989","unstructured":"Rissanen, J. (1989). Stochastic complexity in statistical inquiry. Singapore: World Scientific Publishing."},{"key":"197127_CR28","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1006\/jmla.1996.0032","volume":"35","author":"J.R. Saffran","year":"1996","unstructured":"Saffran, J.R., Newport, E.L., & Aslin, R.N. (1996). Word segmentation: The role of distributional cues. Journal of Memory and Language, 35, 606\u2013621.","journal-title":"Journal of Memory and Language"},{"key":"197127_CR29","volume-title":"Bayesian learning of probabilistic language models","author":"A. Stolcke","year":"1994","unstructured":"Stolcke, A. (1994). Bayesian learning of probabilistic language models. Unpublished doctoral dissertation, University of California at Berkeley."},{"key":"197127_CR30","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1093\/comjnl\/11.2.185","volume":"11","author":"C.S. Wallace","year":"1968","unstructured":"Wallace, C.S., & Boulton, D.M. (1968). An information measure for classification. Computer Journal, 11, 185\u2013194.","journal-title":"Computer Journal"},{"key":"197127_CR31","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1109\/18.87000","volume":"37","author":"I.H. Witten","year":"1991","unstructured":"Witten, I.H., & Bell, T.C. (1991). The zero-frequency problem: Estimating the probabilities of novel events in adaptive text compression. IEEE Transactions on Information Theory, 37, 1085\u20131094.","journal-title":"IEEE Transactions on Information Theory"},{"key":"197127_CR32","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/0271-5309(82)90035-0","volume":"2","author":"J.G. Wolff","year":"1982","unstructured":"Wolff, J.G. (1982). Language acquisition, data compression, and generalization. Language and Communication, 2, 57\u201389.","journal-title":"Language and Communication"},{"key":"197127_CR33","volume-title":"The psycho-biology of language","author":"G.K. Zipf","year":"1935","unstructured":"Zipf, G.K. (1935). The psycho-biology of language. Boston: Houghton Mifflin."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1007541817488.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1007541817488\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1007541817488.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T11:31:24Z","timestamp":1752147084000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1007541817488"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1999,2]]},"references-count":33,"journal-issue":{"issue":"1-3","published-print":{"date-parts":[[1999,2]]}},"alternative-id":["197127"],"URL":"https:\/\/doi.org\/10.1023\/a:1007541817488","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[1999,2]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}