{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T09:27:46Z","timestamp":1767864466818,"version":"3.49.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2003,9,1]],"date-time":"2003-09-01T00:00:00Z","timestamp":1062374400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2003,9,1]],"date-time":"2003-09-01T00:00:00Z","timestamp":1062374400000},"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":["Information Retrieval"],"published-print":{"date-parts":[[2003,9]]},"DOI":"10.1023\/a:1026028229881","type":"journal-article","created":{"date-parts":[[2003,10,24]],"date-time":"2003-10-24T23:17:50Z","timestamp":1067037470000},"page":"333-362","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":52,"title":["Applying Machine Learning to Text Segmentation for Information Retrieval"],"prefix":"10.1007","volume":"6","author":[{"given":"Xiangji","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuchun","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dale","family":"Schuurmans","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nick","family":"Cercone","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen E.","family":"Robertson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"5252213_CR1","unstructured":"Beaulieu M, Gatford M, Huang X, Robertson S, Walker S and Williams P (1997) Okapi at TREC-5. In: Harman DK, Ed., Proceedings of TREC-5, pp. 143\u2013166."},{"key":"5252213_CR2","unstructured":"Bell T, Cleary J and Witten I (1990) Text Compression. Prentice Hall."},{"key":"5252213_CR3","doi-asserted-by":"crossref","unstructured":"Brent M and Tao X (2001) Chinese text segmentation with MBDP-1: Making the most of training corpora. In: Proceedings of ACL2001, France.","DOI":"10.3115\/1073012.1073025"},{"key":"5252213_CR4","doi-asserted-by":"crossref","unstructured":"Buckley C, Singhal A and Mitra M (1997) Using query zoning and correlation within SMART: TREC-5. In: Proceedings of TREC-5, pp. 105\u2013118.","DOI":"10.6028\/NIST.SP.500-238.adhoc-Cornell"},{"key":"5252213_CR5","doi-asserted-by":"crossref","unstructured":"Buckley C, Walz J, Mitra M and Cardie C (1998) Using clustering and superConcepts within SMART: TREC-6. In: Proceedings of TREC-6, pp. 107\u2013124.","DOI":"10.6028\/NIST.SP.500-240.routing-Cornell"},{"key":"5252213_CR6","unstructured":"Chang J-S and Su K-Y (1997) An unsupervised iterative method for Chinese new Lexicon extraction. International Journal of Computational Linguistics & Chinese Language Processing."},{"key":"5252213_CR7","doi-asserted-by":"crossref","unstructured":"Chen A, He J, Xu L, Gey F CandMeggs J (1997) Chinese text retrieval without using a dictionary. In: Proceedings of the 20th Annual International ACMSIGIR Conference on Research and Development in Information Retrieval, ACM, pp. 42\u201349.","DOI":"10.1145\/258525.258532"},{"key":"5252213_CR8","doi-asserted-by":"crossref","unstructured":"Chien L-F, Huang T-I and Chien M-C (1997) Pat-tree-based keyword extraction for Chinese information retrieval. In: Proceedings of the 20th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM, pp. 50\u201358.","DOI":"10.1145\/258525.258534"},{"issue":"4","key":"5252213_CR9","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1109\/TCOM.1984.1096090","volume":"32","author":"J Cleary","year":"1984","unstructured":"Cleary J and Witten I (1984) Data compression using adaptive coding and partial string matching. IEEE Trans on Communications, 32(4):396\u2013402.","journal-title":"IEEE Trans on Communications"},{"key":"5252213_CR10","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1037\/0096-3445.128.2.165","volume":"128","author":"D Dahan","year":"1999","unstructured":"Dahan D and Brent M (1999) On the discovery of novel word-like units from utterances: An artificiallanguage study with implications for native-language acquisition. Journal of Experimental Psychology: General, 128:165\u2013185.","journal-title":"Journal of Experimental Psychology: General"},{"key":"5252213_CR11","doi-asserted-by":"crossref","unstructured":"Dempster A, Laird N and Rubin D (1977) Maximum-likelihood from incomplete data via the EM algorithm. J. Royal Statist. Soc. Ser., B(39).","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"},{"key":"5252213_CR12","unstructured":"Foo S and Li H (2001) Chinese word segmentation accuracy and its effects on information retrieval. TEXT Technology."},{"key":"5252213_CR13","unstructured":"Fung P (1998) Extracting key terms from Chinese and Japnese text. International Journal on Computer Processing of Oriental Language, Special Issue on Information Retrieval on Oriental Languages, 99\u2013121."},{"key":"5252213_CR14","doi-asserted-by":"crossref","unstructured":"Ge X, Pratt W and Smyth P (1999) Discovering Chinese words from unsegmented text. In: Proceedings of the 22th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 271\u2013272.","DOI":"10.1145\/312624.313472"},{"key":"5252213_CR15","doi-asserted-by":"crossref","unstructured":"Gey F, Chen A, He J, Xu L and Meggs J (1996) Term importance, boolean conjunct training, negative terms, and foreign language retrieval: Probabilistic algorithms at TREC-5. In: Proceedings of the Fifth Text REtrieval Conference, pp. 181\u2013190. NIST special publication.","DOI":"10.6028\/NIST.SP.500-238.Spanish-Berkeley"},{"issue":"1","key":"5252213_CR16","first-page":"69","volume":"8","author":"J Hockenmaier","year":"1998","unstructured":"Hockenmaier J and Brew C (1998) Error driven segmentation of Chinese. Communications of COLIPS, 8(1):69\u2013 84.","journal-title":"Communications of COLIPS"},{"key":"5252213_CR17","doi-asserted-by":"crossref","unstructured":"Hofmann T (1999) Probabilistic latent semantic indexing. In: Proceedings of the 22th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM.","DOI":"10.1145\/312624.312649"},{"key":"5252213_CR18","doi-asserted-by":"crossref","unstructured":"Huang X and Roberton S (1998) Okapi Chinese text retrieval experiments at TREC-6. In: Proceedings of TREC-6, pp. 137\u2013142.","DOI":"10.6028\/NIST.SP.500-240.chinese-City"},{"key":"5252213_CR19","unstructured":"Huang X and Robertson S (2000) A probabilistic approach to Chinese information retrieval: Theory and experiments. In: Proceedings of the BCS-IRSG 2000: the 22nd Annual Colloquium on Information Retrieval Research, Cambridge, England."},{"key":"5252213_CR20","unstructured":"Jin W(1992) Chinese segmentation and its disambiguation. In: MCCS-92-227, Computing Research Laboratory, New Mexico State University, Las Cruces, New Mexico."},{"key":"5252213_CR21","doi-asserted-by":"crossref","unstructured":"Kwok KL (1997) Comparing representations in Chinese information retrieval. In: Proceedings of the 20th Annual InternationalACMSIGIR Conference on Research and Development in Information Retrieval,ACM, pp. 34\u201341.","DOI":"10.1145\/258525.258531"},{"issue":"8","key":"5252213_CR22","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1002\/(SICI)1097-4571(1999)50:8<709::AID-ASI8>3.0.CO;2-V","volume":"50","author":"KL Kwok","year":"1999","unstructured":"Kwok KL (1999) Employing multiple representations for Chinese information retrieval. Journal of the American Society for Information Science (JASIS), 50(8):709\u2013723.","journal-title":"Journal of the American Society for Information Science"},{"issue":"4","key":"5252213_CR23","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1023\/A:1009955715597","volume":"3","author":"KL Kwok","year":"2000","unstructured":"Kwok KL (2000) Improving English and Chinese ad-hoc retrieval:Atipster text phase 3 project report. Information Retrieval, 3(4):313\u2013338.","journal-title":"Information Retrieval"},{"key":"5252213_CR24","doi-asserted-by":"crossref","unstructured":"Kwok KLand Grunfeld L (1996) TREC-5 English and Chinese retrieval experiments using PIRCS. In: Proceedings of TREC-5.","DOI":"10.6028\/NIST.SP.500-238.CUNY"},{"key":"5252213_CR25","volume-title":"Foundations of Statistical Natural Language Processing","author":"C Manning","year":"1999","unstructured":"Manning C and Sch\u00fctze H(1999). Foundations of Statistical Natural Language Processing. MIT Press, Cambridge, Massachusetts."},{"key":"5252213_CR26","doi-asserted-by":"crossref","unstructured":"Nie JY, Gao J, Zhang J, and Zhou M (2000) On the use of words and n-grams for chinese information retrieval. In: Proceedings of the Fifth International Workshop on Information Retrieval with Asian Languages (IRAL), Hong kong.","DOI":"10.1145\/355214.355235"},{"key":"5252213_CR27","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/S0306-4573(98)00051-X","volume":"35","author":"JY Nie","year":"1999","unstructured":"Nie JY and Ren F (1999) Chinese information retrieval: Using characters or words? Information Processing and Management, 35:443\u2013462.","journal-title":"Information Processing and Management"},{"key":"5252213_CR28","doi-asserted-by":"crossref","unstructured":"Nie JY, Ren X and Brisebois M(1996) On Chinese text retrieval. In: Proceedings of the 19th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM, pp. 225\u2013233.","DOI":"10.1145\/243199.243270"},{"key":"5252213_CR29","unstructured":"Palmer D and Burger J (1997) Chinese word segmentation and information retrieval. In: AAAI Spring Symposium on Cross-Language Text and Speech Retrieval, Electronic Working Notes."},{"key":"5252213_CR30","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1007\/3-540-44816-0_24","volume-title":"Advances in Intelligent Data Analysis","author":"F Peng","year":"2001","unstructured":"Peng F and Schuurmans D (2001) Self-supervised Chinese word segmentation. In: Hoffman F et al., Eds., Advances in Intelligent Data Analysis, Proceedings of the Fourth International Conference (IDA-01), LNCS 2189, Springer-Verlag, Berlin, Heidelberg, Cascais, Portugal, pp. 238\u2013247."},{"key":"5252213_CR31","unstructured":"Ponte J and Croft W (1996) Useg: A retargetable word segmentation procedure for information retrieval. In: Symposium on Document Analysis and Information Retrival 96 (SDAIR)."},{"key":"5252213_CR32","doi-asserted-by":"crossref","unstructured":"Rabiner L (1989)Atutorial on hidden Markov models and selected applications in speech recognition. Proceedings of IEEE, 77(2).","DOI":"10.1109\/5.18626"},{"key":"5252213_CR33","doi-asserted-by":"crossref","unstructured":"Robertson SE and Walker S (1994) Some simple effective approximations to the 2-Poisson model for probabilistic weighted retrieval. In: Proceedings of the 17th Annual International ACM-SIGIR Conference on Research and Development in Information Retrieval, pp. 232\u2013241.","DOI":"10.1007\/978-1-4471-2099-5_24"},{"key":"5252213_CR34","doi-asserted-by":"crossref","unstructured":"Sparck-Jones K (1979) Search relevance weighting given little relevance information. Journal of Documentation, 35(1).","DOI":"10.1108\/eb026672"},{"issue":"8","key":"5252213_CR35","doi-asserted-by":"crossref","first-page":"558","DOI":"10.1002\/(SICI)1097-4571(199109)42:8<558::AID-ASI4>3.0.CO;2-4","volume":"42","author":"K Sparck-Jones","year":"1991","unstructured":"Sparck-Jones K (1991) The role of artificial intelligence in information retrieval. Journal of the American Society for Information Science, 42(8):558\u2013565.","journal-title":"Journal of the American Society for Information Science"},{"key":"5252213_CR36","first-page":"336","volume":"4","author":"R Sproat","year":"1990","unstructured":"Sproat R and Shih C (1990) A statistical method for finding word boundaries in Chinese text. Computer Processing of Chinese and Oriental Language, 4:336\u2013351.","journal-title":"Computer Processing of Chinese and Oriental Language"},{"issue":"3","key":"5252213_CR37","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1162\/089120100561746","volume":"26","author":"WJ Teahan","year":"2001","unstructured":"Teahan WJ, Wen Y, McNab R and Witten IH (2001) A compression-based algorithm for Chinese word segmentation. Computational Linguistics, 26(3):375\u2013393.","journal-title":"Computational Linguistics"},{"key":"5252213_CR38","doi-asserted-by":"crossref","unstructured":"Voorhees E and Harman D (1998) Overview of the Sixth Text REtrieval Conference (TREC-6). In: Proceedings of the Sixth Text REtrieval Conference (TREC-6). NIST Special Publication.","DOI":"10.6028\/NIST.SP.500-240"},{"key":"5252213_CR39","doi-asserted-by":"crossref","unstructured":"Wilkinson R (1998) Chinese document retrieval at TREC-6. In: Proceedings of TREC-6.","DOI":"10.6028\/NIST.SP.500-240.chinese-overview"},{"issue":"9","key":"5252213_CR40","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1002\/(SICI)1097-4571(199310)44:9<532::AID-ASI3>3.0.CO;2-M","volume":"44","author":"Z Wu","year":"1993","unstructured":"Wu Z and Tseng G (1993) Chinese text segmentation for text retrieval: Achievements and problems. Journal of the American Society for Information Science, 44(9):532\u2013542.","journal-title":"Journal of the American Society for Information Science"}],"container-title":["Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1026028229881.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1026028229881\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1026028229881.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T12:13:31Z","timestamp":1748348011000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1026028229881"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,9]]},"references-count":40,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2003,9]]}},"alternative-id":["5252213"],"URL":"https:\/\/doi.org\/10.1023\/a:1026028229881","relation":{},"ISSN":["1386-4564","1573-7659"],"issn-type":[{"value":"1386-4564","type":"print"},{"value":"1573-7659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2003,9]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}