{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T03:04:29Z","timestamp":1781665469784,"version":"3.54.5"},"reference-count":25,"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:1007506220214","type":"journal-article","created":{"date-parts":[[2002,12,22]],"date-time":"2002-12-22T05:04:10Z","timestamp":1040533450000},"page":"177-210","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":347,"title":["Statistical Models for Text Segmentation"],"prefix":"10.1007","volume":"34","author":[{"given":"Doug","family":"Beeferman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Berger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Lafferty","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"197133_CR1","doi-asserted-by":"crossref","unstructured":"Beeferman, D., Berger, A., & Lafferty, J. (1997). A model of lexical attraction and repulsion. Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics.","DOI":"10.3115\/976909.979665"},{"issue":"1","key":"197133_CR2","first-page":"39","volume":"22","author":"A. Berger","year":"1996","unstructured":"Berger, A., Della Pietra, S., & Della Pietra, V. (1996).A maximum entropy approach to natural language processing. Computational Linguistics, 22(1), 39\u201371.","journal-title":"Computational Linguistics"},{"key":"197133_CR3","volume-title":"Classification and regression trees","author":"L. Breiman","year":"1984","unstructured":"Breiman, L., Friedman, J., Olshen, R., & Stone, C. (1984). Classification and regression trees. Belmont, Wadsworth."},{"issue":"4","key":"197133_CR4","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1145\/205323.205337","volume":"38","author":"M. Christel","year":"1995","unstructured":"Christel, M., Kanade, T., Mauldin, M., Reddy, R., Sirbu, M., Stevens, S., & Wactlar, H. (1995). Informedia digital video library. Communications of the ACM, 38(4), 57\u201358.","journal-title":"Communications of the ACM"},{"issue":"4","key":"197133_CR5","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1109\/34.588021","volume":"19","author":"S. Della Pietra","year":"1997","unstructured":"Della Pietra, S., Della Pietra, V., & Lafferty, J. (1997). Inducing features of random fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(4), 380\u2013393.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"197133_CR6","doi-asserted-by":"crossref","DOI":"10.1201\/9780429258411","volume-title":"Bayesian data analysis","author":"A. Gelman","year":"1995","unstructured":"Gelman, A., Carlin, J., Stern, H., & Rubin, D. (1995). Bayesian data analysis. London: Chapman & Hall."},{"key":"197133_CR7","unstructured":"Hastie, T., & Tibshirani, R. (1990). Generalized additive models. Chapman and Hall."},{"key":"197133_CR8","doi-asserted-by":"crossref","unstructured":"Hearst, M.A. (1994). Multi-paragraph segmentation of expository text. Proceedings of the 32nd Annual Meeting of the Association for Computational Linguistics.","DOI":"10.3115\/981732.981734"},{"issue":"1","key":"197133_CR9","first-page":"33","volume":"23","author":"M.A. Hearst","year":"1997","unstructured":"Hearst, M.A. (1997). TextTiling: Segmenting text into multi-paragraph subtopic passages. Computational Linguistics, 23(1), 33\u201364.","journal-title":"Computational Linguistics"},{"issue":"3","key":"197133_CR10","first-page":"501","volume":"19","author":"J. Hirschberg","year":"1993","unstructured":"Hirschberg, J., & Litman, D.J. (1993). Disambiguation of cue phrases. Computational Linguistics, 19(3), 501\u2013530.","journal-title":"Computational Linguistics"},{"key":"197133_CR11","doi-asserted-by":"crossref","unstructured":"Jelinek, F., Merialdo, B., Roukos, S., & Strauss, M. (1991). A dynamic language model for speech recognition. Proceedings of the DARPA Speech and Natural Language Workshop (pp. 293\u2013295).","DOI":"10.3115\/112405.112464"},{"issue":"3","key":"197133_CR12","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1109\/TASSP.1987.1165125","volume":"ASSP-35","author":"S. Katz","year":"1987","unstructured":"Katz, S. (1987). Estimation of probabilities from sparse data for the language model component of a speech recognizer. IEEE Transactions on Acoustics, Speech and Signal Processing, ASSP-35(3), 400\u2013401.","journal-title":"IEEE Transactions on Acoustics, Speech and Signal Processing"},{"key":"197133_CR13","doi-asserted-by":"crossref","unstructured":"Kozima, H. (1993). Text segmentation based on similarity between words. Proceedings of the 31st Annual Meeting of the Association for Computational Linguistics.","DOI":"10.3115\/981574.981616"},{"key":"197133_CR14","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1109\/34.56193","volume":"12","author":"R. Kuhn","year":"1990","unstructured":"Kuhn, R., & de Mori, R. (1990). A cache-based natural language model for speech recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12, 570\u2013583.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"197133_CR15","unstructured":"Lafferty, J. (1993). Barking up the right tree: Estimating & #x03BB; & #x2019;s for decision trees using the EM algorithm. IBM Research Report."},{"key":"197133_CR16","doi-asserted-by":"crossref","unstructured":"Lau, R., Rosenfeld, R., & Roukos, S. (1993). Adaptive language modeling using the maximum entropy principle. Proceedings of the ARPA Human Language TechnologyWorkshop (pp. 108\u2013113). Morgan Kaufman Publishers.","DOI":"10.3115\/1075671.1075695"},{"key":"197133_CR17","doi-asserted-by":"crossref","unstructured":"Litman, D.J., & Passonneau, R.J. (1995). Combining multiple knowledge sources for discourse segmentation. Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics.","DOI":"10.3115\/981658.981673"},{"issue":"1","key":"197133_CR18","first-page":"103","volume":"23","author":"R.J. Passoneau","year":"1997","unstructured":"Passoneau, R.J., & Litman, D.J. (1997). Discourse segmentation by human and automated means. Computational Linguistics, 23(1), 103\u2013139.","journal-title":"Computational Linguistics"},{"key":"197133_CR19","doi-asserted-by":"crossref","unstructured":"Ponte, J., & Croft, W.B. (1997). Text segmentation by topic. Proceedings of the First European Conference on Research and Advanced Technology for Digital Libraries (pp. 120\u2013129).","DOI":"10.1007\/BFb0026725"},{"key":"197133_CR20","doi-asserted-by":"crossref","unstructured":"Reynar, J.C. (1994). An automatic method of finding topic boundaries. Proceedings of the 32nd Annual Meeting of the Association for Computational Linguistics.","DOI":"10.3115\/981732.981783"},{"key":"197133_CR21","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1006\/csla.1996.0011","volume":"10","author":"R. Rosenfeld","year":"1996","unstructured":"Rosenfeld, R. (1996). A maximum entropy approach to adaptive statistical language modeling. Computer Speech and Language, 10, 187\u2013228.","journal-title":"Computer Speech and Language"},{"key":"197133_CR22","unstructured":"Topic Detection and Tracking Workshop. (1997). Unpublished workshop notes."},{"key":"197133_CR23","doi-asserted-by":"crossref","unstructured":"Xu, J., & Croft, W.B. (1996). Query expansion using local and global document analysis. Proceedings of the Nineteenth Annual ACM SIGIR Conference on Research and Development in Information Retrieval.","DOI":"10.1145\/243199.243202"},{"key":"197133_CR24","unstructured":"Yamron, J. (1998). Topic detection and tracking segmentation task. Broadcast News Transcription and Understanding Workshop."},{"key":"197133_CR25","doi-asserted-by":"crossref","unstructured":"Yamron, J., Carp, I., Gillick, L., Lowe, S., & Van Mulbregt, P. (1998). A hidden Markov model approach to text segmentation and event tracking. Proceedings of the International Conference on Acoustics and Signal Processing (ICASSP).","DOI":"10.1109\/ICASSP.1998.674435"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1007506220214.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1007506220214\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1007506220214.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T11:31:08Z","timestamp":1752147068000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1007506220214"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1999,2]]},"references-count":25,"journal-issue":{"issue":"1-3","published-print":{"date-parts":[[1999,2]]}},"alternative-id":["197133"],"URL":"https:\/\/doi.org\/10.1023\/a:1007506220214","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"}]}}