{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T12:29:00Z","timestamp":1754396940261,"version":"3.41.2"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2000,8,1]],"date-time":"2000-08-01T00:00:00Z","timestamp":965088000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2000,8,1]],"date-time":"2000-08-01T00:00:00Z","timestamp":965088000000},"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":[[2000,8]]},"DOI":"10.1023\/a:1007653929870","type":"journal-article","created":{"date-parts":[[2002,12,22]],"date-time":"2002-12-22T05:54:50Z","timestamp":1040536490000},"page":"111-137","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Stochastic Grammatical Inference of Text Database Structure"],"prefix":"10.1007","volume":"40","author":[{"given":"Matthew","family":"Young-Lai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank WM.","family":"Tompa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"262610_CR1","unstructured":"Ahonen, H. (1996). Generating grammars for structured documents using grammatical inference methods. Ph.D. Thesis, University of Helsinki, Department of Computer Science, Technical Report A-1996\u20134."},{"key":"262610_CR2","doi-asserted-by":"crossref","unstructured":"Ahonen, H., Mannila, H., & Nikunen, E. (1994a). Forming grammars for structured documents: An application of grammatical inference. In Carrasco and Oncina (1994a), pp. 153\u2013167.","DOI":"10.1007\/3-540-58473-0_145"},{"key":"262610_CR3","unstructured":"Ahonen, H., Mannila, H., & Nikunen, E. (1994b). Generating grammars for SGML tagged texts lacking DTD. In M. Murata & H. Gallaire (Eds.), Proc. Workshop on Principles of Document Processing (PODP), Darmstadt."},{"key":"262610_CR4","unstructured":"Andr\u00e9, J., Furuta, R., & Quint, V. (1989). Structured documents. The Cambridge Series on Electronic Publishing. Cambridge University Press."},{"key":"262610_CR5","series-title":"Technical Report","volume-title":"The research potential of the electronic OED2 database at the University of Waterloo: a guide for scholars","author":"D. L. Berg","year":"1989","unstructured":"Berg, D. L. (1989). The research potential of the electronic OED2 database at the University of Waterloo: a guide for scholars. Technical Report OED\u201389\u201302, UW Centre for the New Oxford English Dictionary, Waterloo, Ontario. available at http:\/\/www.chass.utoronto.ca:8080\/cch\/Berg\/Berg-1Contents.html."},{"key":"262610_CR6","volume-title":"A guide to the Oxford English dictionary: The essential companion and user's guide","author":"D. L. Berg","year":"1993","unstructured":"Berg, D. L. (1993). A guide to the Oxford English dictionary: The essential companion and user's guide, Oxford University Press, Oxford."},{"key":"262610_CR7","unstructured":"Bray, T., Paoli, J., & Sperberg-McQueen, C. M. (1998). Extensible markup language (XML) 1.0. w3c recommendation."},{"key":"262610_CR8","unstructured":"Carrasco, R. & Oncina, J. (Eds.). (1994a). Lecture Notes in Computer Science, Vol. 862, Springer-Verlag."},{"key":"262610_CR9","doi-asserted-by":"crossref","unstructured":"Carrasco, R. C. & Oncina, J. (1994b). Learning stochastic regular grammars by means of a state merging method. In Carrasco and Oncina (1994a), pp. 139\u2013152.","DOI":"10.1007\/3-540-58473-0_144"},{"key":"262610_CR10","unstructured":"Chen, J. (1991). Grammar generation and query processing for text databases. Research proposal, University of Waterloo."},{"key":"262610_CR11","series-title":"Technical Report","volume-title":"Finite state transduction tools","author":"D. Clark","year":"1991","unstructured":"Clark, D. (1991). Finite state transduction tools. Technical Report OED\u201391\u201303, UW Centre for the New Oxford English Dictionary and Text Research, Waterloo, Ontario."},{"issue":"11","key":"262610_CR12","doi-asserted-by":"crossref","first-page":"933","DOI":"10.1145\/32206.32209","volume":"30","author":"J. H. Coombs","year":"1987","unstructured":"Coombs, J. H., Renear, A. H., & DeRose, S. J. (1987). Markup systems and the future of scholarly text processing. Communications of the ACM, 30(11), 933\u2013947.","journal-title":"Communications of the ACM"},{"key":"262610_CR13","volume-title":"Sample size methodology","author":"M. Desu","year":"1990","unstructured":"Desu, M. (1990). Sample size methodology. Boston: Academic Press."},{"issue":"4","key":"262610_CR14","first-page":"447","volume":"6","author":"P. Fankhauser","year":"1993","unstructured":"Fankhauser, P. & Xu, Y. (1993). MarkItUp! an incremental approach to document structure recognition. Electronic Publishing-Origin, Dissemination and Design, 6(4), 447\u2013456.","journal-title":"Electronic Publishing-Origin, Dissemination and Design"},{"key":"262610_CR15","unstructured":"Fr\u00f6hlich, M. & Werner, M. (1995). da Vinci 1.4 User Manual. available from daVinci@informatik.unibremen.de."},{"key":"262610_CR16","volume-title":"Syntactic pattern recognition and applications","author":"K. S. Fu","year":"1982","unstructured":"Fu, K. S. (1982). Syntactic pattern recognition and applications. Englewood Cliffs, N.J: Prentice-Hall."},{"key":"262610_CR17","unstructured":"Goldman, R. & Widom, J. (1997). DataGuides: Enabling query formulation and optimization in semistructured databases. In Proceedings of the Twenty-Third International Conference onVery Large Databases (pp. 436\u2013445). Athens, Greece."},{"key":"262610_CR18","first-page":"339","volume":"13","author":"G. Gonnet","year":"1987","unstructured":"Gonnet, G. & Tompa, F. W. (1987). Mind your grammar: a new approach to modelling text. Very Large Data Bases (VLDB), 13, 339\u2013346.","journal-title":"Very Large Data Bases (VLDB)"},{"key":"262610_CR19","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1080\/01621459.1963.10500830","volume":"58","author":"W. Hoeffding","year":"1963","unstructured":"Hoeffding, W. (1963). Probability inequalities for sums of bounded random variables. American Statistical Association Journal, 58, 13\u201330.","journal-title":"American Statistical Association Journal"},{"key":"262610_CR20","unstructured":"Holte, R. C., Acker, L. E., & Porter, B.W. (1989). Concept learning and the problem of small disjuncts, Sridharan, N. (Ed.), Proceedings of the Eleventh International Joint Conference on Artificial Intelligence V. 1, Detroit, Michigan."},{"key":"262610_CR21","volume-title":"Introduction to automata theory, languages and computation","author":"J. E. Hopcroft","year":"1979","unstructured":"Hopcroft, J. E. & Ullman, J. D. (1979). Introduction to automata theory, languages and computation. Reading, Massachusetts: Addison-Wesley."},{"key":"262610_CR22","volume-title":"Oxford advanced learner's dictionary of current English","author":"A. S. Hornby","year":"1992","unstructured":"Hornby, A. S. & Cowie, A. P. (1992). Oxford advanced learner's dictionary of current English 4th edn. Oxford: Oxford University Press.","edition":"4th edn"},{"key":"262610_CR23","unstructured":"Huang, X., Ariki, Y., & Jack, M. (1990). Hidden markov models for speech recognition. Edinburgh University Press."},{"key":"262610_CR24","unstructured":"ISO (1986). Information processing\u2014text and office systems\u2014standard generalized markup language (SGML)."},{"key":"262610_CR25","unstructured":"Kazman, R. (1986). Structuring the text of the Oxford English dictionary through finite state transduction. Technical Report CS\u201386\u201320, University of Waterloo, Computer Science Department."},{"key":"262610_CR26","unstructured":"Kilpel\u00e4inen, P., Lind\u00e9n, G., Mannila, H., & Nikunen, E. (1990). A structured document database system. In Furuta, R. (Ed.), In EP90-Proceedings of the International Conference on Electronic Publishing, Document Manipulation & Typography, The Cambridge Series on Electronic Publishing. Cambridge University Press."},{"key":"262610_CR27","unstructured":"Krogh, C. M. (Ed.). (1995). Compendium of pharmaceuticals and specialties, 30th edn. Canadian Pharmaceutical Association."},{"issue":"10","key":"262610_CR28","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1145\/359842.359853","volume":"20","author":"W. Lalonde","year":"1977","unstructured":"Lalonde, W. (1977). Regular right part grammars and their parsers. Communications of the ACM, 20(10), 731\u2013741.","journal-title":"Communications of the ACM"},{"key":"262610_CR29","unstructured":"Lang, K. J., Pearlmutter, B. A., & Price, R. A. (2000). Results of the Abbadingo one DFA learning competition and a new evidence driven state merging algorithm To appear."},{"key":"262610_CR30","first-page":"34","volume":"4","author":"K. Lari","year":"1990","unstructured":"Lari, K. & Young, S. (1990). The estimation of stochastic context-free grammars using the inside-outside algorithm. Comp. Speech and Language, 4, 34\u201336.","journal-title":"Comp. Speech and Language"},{"issue":"3","key":"262610_CR31","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1145\/262762.262770","volume":"26","author":"J. McHugh","year":"1997","unstructured":"McHugh, J., Abiteboul, S., Goldman, R., Quass, D., amp; Widom, J. (1997). Lore: a database management system for semistructured data. SIGMOD Record, 26(3), 54\u201366.","journal-title":"SIGMOD Record"},{"key":"262610_CR32","unstructured":"Muslea, I., Minton, S., & Knoblock, C. (1998). Wrapper induction for semistructured, web-based information sources. In Proceedings of the Conference on Automatic Learning and Discovery (CONALD-98)."},{"key":"262610_CR33","doi-asserted-by":"crossref","unstructured":"Oncina, J. & Garc\u00eda, P. (1992). Inferring regular languages in polynomial updated time. In N. P. de la Blanca, A. Sanfeliu, & E. Vidal (Eds.), Pattern Recognition and Image Analysis, pp. 49\u201361. World Scientific. Oxford University Press (1998). Inside the Oxford English Dictionary. http:\/\/www.oed.com.","DOI":"10.1142\/9789812797902_0004"},{"key":"262610_CR34","unstructured":"Raymond, D. R. (1993). Visualizing text. In 9th Annual Conference of the UW Centre for the New OED, Oxford, England. available at http:\/\/solo.uwaterloo.ca\/\u223cdrraymon\/papers\/oed93.ps."},{"key":"262610_CR35","doi-asserted-by":"crossref","unstructured":"Ron, D., Singer, Y., & Tishby, N. (1995). On the learnability and usage of acyclic probabilistic automata. In Computational Learning Theory, COLT 95 (pp. 31\u201340).","DOI":"10.1145\/225298.225302"},{"key":"262610_CR36","doi-asserted-by":"crossref","unstructured":"S\u00e1nchez, J. A. & Bened\u00ed, J. M. (1994). Statistical inductive learning of regular formal languages. In Carrasco and Oncina (1994a), pp. 130\u2013138.","DOI":"10.1007\/3-540-58473-0_143"},{"key":"262610_CR37","unstructured":"Shafer, K. (1995). Creating DTDs via the GB-engine and Fred. OCLC Fred web page http:\/\/www.oclc.org\/fred."},{"key":"262610_CR38","volume-title":"The Oxford English dictionary","year":"1989","unstructured":"Simpson, J. & Weiner, E. (Eds.). (1989). The Oxford English dictionary, 2nd edn. Oxford: Clarendon Press.","edition":"2nd edn."},{"key":"262610_CR39","doi-asserted-by":"crossref","unstructured":"Stolcke, A. & Omohundro, S. (1994). Inducing probabilistic grammars by Bayesian model merging. In Carrasco and Oncina (1994a), pp. 106\u2013118.","DOI":"10.1007\/3-540-58473-0_141"},{"volume-title":"Proc. of the Workshop on Managment of Semi-structured Data (PODS\/SIGMOD)","year":"1997","key":"262610_CR40","unstructured":"Suciu, D. (Ed.). (1997). In Proc. of the Workshop on Managment of Semi-structured Data (PODS\/SIGMOD), Tucson, Arizona. National Science Foundation. available at http:\/\/www.research.att.com\/\u223csuciu\/workshop-papers.html."},{"key":"262610_CR41","doi-asserted-by":"crossref","unstructured":"Vidal, E. (1994). Grammatical inference: an introductory survey. In Carrasco and Oncina (1994a), pp. 1\u20134.","DOI":"10.1007\/3-540-58473-0_131"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1007653929870.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1007653929870\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1007653929870.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T11:42:54Z","timestamp":1752147774000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1007653929870"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2000,8]]},"references-count":41,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2000,8]]}},"alternative-id":["262610"],"URL":"https:\/\/doi.org\/10.1023\/a:1007653929870","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2000,8]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}