{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T05:37:17Z","timestamp":1777441037966,"version":"3.51.4"},"publisher-location":"Berlin, Heidelberg","reference-count":24,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540709381","type":"print"},{"value":"9783540709398","type":"electronic"}],"license":[{"start":{"date-parts":[[2007,1,1]],"date-time":"2007-01-01T00:00:00Z","timestamp":1167609600000},"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":[[2007]]},"DOI":"10.1007\/978-3-540-70939-8_16","type":"book-chapter","created":{"date-parts":[[2007,5,19]],"date-time":"2007-05-19T11:15:01Z","timestamp":1179573301000},"page":"175-185","source":"Crossref","is-referenced-by-count":7,"title":["A Generalized Approach to Word Segmentation Using\u00a0Maximum Length Descending Frequency and\u00a0Entropy Rate"],"prefix":"10.1007","author":[{"given":"Md. Aminul","family":"Islam","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diana","family":"Inkpen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iluju","family":"Kiringa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"16_CR1","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1023\/A:1007541817488","volume":"34","author":"M. Brent","year":"1999","unstructured":"Brent, M.: An efficient, probabilistically sound algorithm for segmentation and word discovery. Machine Learning\u00a034, 71\u2013106 (1999)","journal-title":"Machine Learning"},{"key":"16_CR2","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/S0010-0277(96)00719-6","volume":"61","author":"M. Brent","year":"1996","unstructured":"Brent, M., Cartwright, T.: Distributional regularity and phonotactics are useful for segmentation. Cognition\u00a061, 93\u2013125 (1996)","journal-title":"Cognition"},{"key":"16_CR3","first-page":"748","volume-title":"Proc. of the Twelfth National Conference on Artificial Intelligence","author":"E. Brill","year":"1994","unstructured":"Brill, E.: Some advances in transformation-based part of speech tagging. In: Proc. of the Twelfth National Conference on Artificial Intelligence, pp. 748\u2013753. MIT Press, Cambridge (1994)"},{"key":"16_CR4","unstructured":"Christiansen, M., Allen, J.: Coping with Variation in Speech Segmentation. In: Proceedings of GALA 1997: Language Acquisition: Knowledge Representation and Processing, pp. 327\u2013332 (1997)"},{"key":"16_CR5","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1080\/016909698386528","volume":"13","author":"M. Christiansen","year":"1998","unstructured":"Christiansen, M., Allen, J., Seidenberg, M.: Learning to Segment Speech Using Multiple Cues: A Connectionist Model. Language and Cognitive Processes\u00a013, 221\u2013268 (1998)","journal-title":"Language and Cognitive Processes"},{"key":"16_CR6","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1023\/A:1006506017891","volume":"11","author":"W. Daelamans","year":"1997","unstructured":"Daelamans, W., van den Bosch, A., Weijters, A.: IGTree: Using trees for compression and classification in lazy learning algorithms. Artificial Intelligence Review\u00a011, 407\u2013423 (1997)","journal-title":"Artificial Intelligence Review"},{"key":"16_CR7","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1201\/9780824746346","volume-title":"Handbook of Natural Language Processing","author":"R. Dale","year":"2000","unstructured":"Dale, R., Moisl, H., Somers, H.: Handbook of Natural Language Processing, pp. 22\u201326. Marcel Dekker, Inc., New York (2000)"},{"key":"16_CR8","unstructured":"Deligne, S., Bimbot, F.: Language Modeling by Variable Length Sequences: Theoretical Formulation and Evaluation of Multigrams. In: Proceedings ICASSP (1995)"},{"key":"16_CR9","unstructured":"de Marcken, C.: The Unsupervised Acquisition of a Lexicon from Continuous Speech. Technical Report AI Memo No. 1558, M.I.T., Cambridge, Massachusetts (1995)"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Do, H.H., Rahm, E.: COMA \u2013 A System for Flexible Combination of Schema Matching Approaches. In: VLDB (2002)","DOI":"10.1016\/B978-155860869-6\/50060-3"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Fung, P., Wu, D.: Improving Chinise tokenization with linguistic filters on statistical lexical acquisition. In: Fourth Conference Applied Natural Language Processing, Stuttgart, pp. 180\u2013181 (1994)","DOI":"10.3115\/974358.974399"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Gao, J., Li, M., Wu, A., Huang, C.-N.: Chinese word segmentation and named entity recognition: a pragmatic approach. Computational Linguistics\u00a031(4) (2005)","DOI":"10.1162\/089120105775299177"},{"key":"16_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/978-3-540-30463-0_54","volume-title":"Progress in Pattern Recognition, Image Analysis and Applications","author":"A. Gelbukh","year":"2004","unstructured":"Gelbukh, A., Alexandrov, M., Han, S.Y.: Detecting Inflection Patterns in Natural Language by Minimization of Morphological Model. In: Sanfeliu, A., Mart\u00ednez Trinidad, J.F., Carrasco Ochoa, J.A. (eds.) CIARP 2004. LNCS, vol.\u00a03287, pp. 432\u2013438. Springer, Heidelberg (2004)"},{"key":"16_CR14","unstructured":"Hua, Y.: Unsupervised word induction using MDL criterion. In: Proceedings ISCSL2000, Beijing (2000)"},{"key":"16_CR15","unstructured":"Kit, C., Wilks, Y.: Unsupervised Learning of Word Boundary with Description Length Gain. In: Proceedings CoNLL99 ACL Workshop, Bergen (1999)"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Madhavan, J., Bernstein, P., Doan, A., Halevy, A.: Corpus-based Schema Matching. In: International Conference on Data Engineering (ICDE-05) (2005)","DOI":"10.1109\/ICDE.2005.39"},{"issue":"3","key":"16_CR17","first-page":"405","volume":"23","author":"A. Mikheev","year":"1997","unstructured":"Mikheev, A.: Automatic rule induction for unknown word guessing. Computational Linguistics\u00a023(3), 405\u2013423 (1997)","journal-title":"Computational Linguistics"},{"key":"16_CR18","unstructured":"Peng, F., Schuurmans, D.: A Hierarchical EM Approach to Word Segmentation. In: Proceedings of the Sixth Natural Language Processing Pacific Rim Symposium (NLPRS 2001) Tokyo, Japan, pp. 475\u2013480 (2001)"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Rabiner, L.: A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings of IEEE\u00a077(2) (1989)","DOI":"10.1109\/5.18626"},{"key":"16_CR20","doi-asserted-by":"crossref","first-page":"216","DOI":"10.7551\/mitpress\/5236.001.0001","volume-title":"Parallel distributed processing, vol. II","author":"D.E. Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., McClelland, J.: On learning the past Tense of English verbs. In: Parallel distributed processing, vol. II, pp. 216\u2013271. MIT Press, Cambridge (1986)"},{"key":"16_CR21","doi-asserted-by":"publisher","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.: Word segmentation: The role of distributional cues. Journal of Memory and Language\u00a035, 606\u2013621 (1996)","journal-title":"Journal of Memory and Language"},{"key":"16_CR22","volume-title":"The mathematical theory of communication","author":"C.E. Shannon","year":"1963","unstructured":"Shannon, C.E., Weaver, W.: The mathematical theory of communication. University of Illinois Press, Urbana (1963)"},{"issue":"3","key":"16_CR23","first-page":"377","volume":"22","author":"R. Sproat","year":"1996","unstructured":"Sproat, R., Shih, C., Gale, W., Chang, N.: A stochastic finite-state word-segmentation algorithm for Chinese. Computational Linguistics\u00a022(3), 377\u2013404 (1996)","journal-title":"Computational Linguistics"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Sproat, R., Shih, C., Gale, W., Chang, N.: A stochastic word segmentation algorithm for a Mandarin text-to-speech system. In: 32nd Annual Meeting of the Association for Computational Linguistics, Las Cruces, NM, pp. 66\u201372 (1994)","DOI":"10.3115\/981732.981742"}],"container-title":["Lecture Notes in Computer Science","Computational Linguistics and Intelligent Text Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-70939-8_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T13:04:57Z","timestamp":1737032697000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-70939-8_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"ISBN":["9783540709381","9783540709398"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-70939-8_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2007]]}}}