{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T08:23:23Z","timestamp":1725524603232},"publisher-location":"Berlin, Heidelberg","reference-count":25,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540929949"},{"type":"electronic","value":"9783540929956"}],"license":[{"start":{"date-parts":[[2008,1,1]],"date-time":"2008-01-01T00:00:00Z","timestamp":1199145600000},"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":[[2008]]},"DOI":"10.1007\/978-3-540-92995-6_7","type":"book-chapter","created":{"date-parts":[[2009,1,9]],"date-time":"2009-01-09T09:02:58Z","timestamp":1231491778000},"page":"91-106","source":"Crossref","is-referenced-by-count":2,"title":["Ad Hoc Data and the Token Ambiguity Problem"],"prefix":"10.1007","author":[{"given":"Qian","family":"Xi","sequence":"first","affiliation":[]},{"given":"Kathleen","family":"Fisher","sequence":"additional","affiliation":[]},{"given":"David","family":"Walker","sequence":"additional","affiliation":[]},{"given":"Kenny Q.","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"3","key":"7_CR1","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1145\/322326.322334","volume":"29","author":"D. Angluin","year":"1982","unstructured":"Angluin, D.: Inference of reversible languages. Journal of the ACM\u00a029(3), 741\u2013765 (1982)","journal-title":"Journal of the ACM"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Arasu, A., Garcia-Molina, H.: Extracting structured data from web pages. In: SIGMOD, pp. 337\u2013348 (2003)","DOI":"10.1145\/872757.872799"},{"key":"7_CR3","unstructured":"Bex, G.J., Neven, F., Schwentick, T., Tuyls, K.: Inference of concise DTDs from XML data. In: VLDB, pp. 115\u2013126 (2006)"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Borkar, V., Deshmukh, K., Sarawagi, S.: Automatic segmentation of text into structured records. In: SIGMOD, New York, NY, USA, pp. 175\u2013186 (2001)","DOI":"10.1145\/375663.375682"},{"key":"7_CR5","unstructured":"Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines. Software (2001), http:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvm"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Chen, S.F.: Bayesian grammar induction for language modeling. In: Proceedings of the 33rd Annual Meeting of the ACL, pp. 228\u2013235 (1995)","DOI":"10.3115\/981658.981689"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Fisher, K., Gruber, R.: PADS: A domain specific language for processing ad hoc data. In: PLDI, pp. 295\u2013304 (June 2005)","DOI":"10.1145\/1065010.1065046"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Fisher, K., Walker, D., Zhu, K.Q.: LearnPADS: Automatic tool generation from ad hoc data. In: SIGMOD (June 2008)","DOI":"10.1145\/1376616.1376759"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Fisher, K., Walker, D., Zhu, K.Q., White, P.: From dirt to shovels: Fully automatic tool generation from ad hoc data. In: POPL (January 2008)","DOI":"10.1145\/1328438.1328488"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Garofalakis, M.N., Gionis, A., Rastogi, R., Seshadri, S., Shim, K.: XTRACT: A system for extracting document type descriptors from XML documents. In: SIGMOD, pp. 165\u2013176 (2000)","DOI":"10.1145\/342009.335409"},{"issue":"5","key":"7_CR11","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1016\/S0019-9958(67)91165-5","volume":"10","author":"E.M. Gold","year":"1967","unstructured":"Gold, E.M.: Language identification in the limit. Information and Control\u00a010(5), 447\u2013474 (1967)","journal-title":"Information and Control"},{"key":"7_CR12","unstructured":"Craig\u2019s List (2008), http:\/\/www.craigslist.org\/"},{"key":"7_CR13","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4643.001.0001","volume-title":"The Minimum Description Length Principle","author":"P.D. Gr\u00fcnwald","year":"2007","unstructured":"Gr\u00fcnwald, P.D.: The Minimum Description Length Principle. MIT Press, Cambridge (2007)"},{"issue":"4","key":"7_CR14","first-page":"527","volume":"25","author":"P.A. Heeman","year":"1999","unstructured":"Heeman, P.A., Allen, J.F.: Speech repairs, intonational phrases and discourse markers: Modeling speakers\u2019 utterances in spoken dialog. Computational Linguistics\u00a025(4), 527\u2013571 (1999)","journal-title":"Computational Linguistics"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Hong, T.W.: Grammatical Inference for Information Extraction and Visualisation on the Web. Ph.D. Thesis, Imperial College, London (2002)","DOI":"10.1007\/3-540-44794-6_18"},{"key":"7_CR16","unstructured":"Kulp, D., Haussler, D., Reese, M.G., Eeckman, F.H.: A generalized hidden markov model for the recognition of human genes in DNA. In: Proceedings of the Fourth International Conference on Intelligent Systems for Molecular Biology, pp. 134\u2013141 (1996)"},{"key":"7_CR17","unstructured":"Kushmerick, N.: Wrapper induction for information extraction. PhD thesis, University of Washington, Department of Computer Science and Engineering (1997)"},{"key":"7_CR18","unstructured":"Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: ICML, pp. 282\u2013289 (2001)"},{"key":"7_CR19","unstructured":"MEGA model optimization package (2007), http:\/\/www.cs.utah.edu\/~hal\/megam\/"},{"key":"7_CR20","unstructured":"PADS project (2007), http:\/\/www.padsproj.org\/"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Pinto, D., McCallum, A., Wei, X., Croft, W.B.: Table extraction using conditional random fields. In: SIGIR, New York, NY, USA, pp. 235\u2013242 (2003)","DOI":"10.1145\/860435.860479"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Rabiner, L.R.: A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE\u00a077(2) (February 1989)","DOI":"10.1109\/5.18626"},{"issue":"1-3","key":"7_CR23","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1023\/A:1007562322031","volume":"34","author":"S. Soderland","year":"1999","unstructured":"Soderland, S.: Learning information extraction rules for semi-structured and free text. Machine Learning\u00a034(1-3), 233\u2013272 (1999)","journal-title":"Machine Learning"},{"key":"7_CR24","unstructured":"Adam, L., Berger, T., Vincent, J., Della Pietra, Stephen, A.: A maximum entropy approach to natural language processing. Computational Linguistics\u00a022(1) (March 1996)"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Vidal, E.: Grammatical inference: An introduction survey. In: ICGI, pp. 1\u20134 (1994)","DOI":"10.1007\/3-540-58473-0_131"}],"container-title":["Lecture Notes in Computer Science","Practical Aspects of Declarative Languages"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-92995-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,17]],"date-time":"2019-05-17T00:33:25Z","timestamp":1558053205000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-92995-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008]]},"ISBN":["9783540929949","9783540929956"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-92995-6_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2008]]}}}