{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T17:10:10Z","timestamp":1740849010263,"version":"3.38.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Comput. Sci. Technol."],"published-print":{"date-parts":[[2011,1]]},"DOI":"10.1007\/s11390-011-9411-z","type":"journal-article","created":{"date-parts":[[2011,1,11]],"date-time":"2011-01-11T09:57:38Z","timestamp":1294739858000},"page":"14-24","source":"Crossref","is-referenced-by-count":8,"title":["Chinese New Word Identification: A Latent Discriminative Model with Global Features"],"prefix":"10.1007","volume":"26","author":[{"given":"Xiao","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"De-Gen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai-Yu","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fu-Ji","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2011,1,11]]},"reference":[{"key":"9411_CR1","doi-asserted-by":"crossref","unstructured":"Goh C, Asahara M, Matsumoto Y. Chinese unknown word identification using character-based tagging and chunking. In Proc. the 41st Annual Meeting on Association for Computational Linguistics, Sapporo, Japan, Jul. 7-12, 2003, pp.197-200.","DOI":"10.3115\/1075178.1075215"},{"issue":"1","key":"9411_CR2","first-page":"47","volume":"5","author":"J Nie","year":"1995","unstructured":"Nie J, Hannan M, Jin W. Unknown word detection and segmentation of Chinese using statistical and heuristic knowledge. Communications of COLIPS, 1995, 5(1): 47-57.","journal-title":"Communications of COLIPS"},{"key":"9411_CR3","unstructured":"Chen C, Bai M, Chen K. Category guessing for Chinese unknown words. In Proc. the Natural Language Processing Pacific Rim Symposium, Phuket, Thailand, Dec. 2-4, 1997, pp.35-40."},{"issue":"2","key":"9411_CR4","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, 1996, 22(2): 377-404.","journal-title":"Computational Linguistics"},{"key":"9411_CR5","unstructured":"Zheng J H, Li W H. A study on automatic identification for Internet new words according to word-building rule. Journal of Shanxi University (Natural Science Edition), 2002, 25(2): 115-119. (In Chinese)"},{"key":"9411_CR6","unstructured":"Yan W. New words mining from the dynamic current corpus based on VSM. In Proc. Dictionaries and Digital Symposium, Yantai, China, Aug. 16-20, 2004. (In Chinese)"},{"key":"9411_CR7","doi-asserted-by":"crossref","unstructured":"Chen A. Chinese word segmentation using minimal linguistic knowledge. In Proc. the Second SIGHAN Workshop on Chinese Language Processing, Sapporo, Japan, Jul. 11-12, 2003, pp.148-151.","DOI":"10.3115\/1119250.1119271"},{"key":"9411_CR8","doi-asserted-by":"crossref","unstructured":"Wu A D, Jiang Z X. Statistically-enhanced new word identification in a rule-based Chinese system. In Proc. the Second Chinese Language Processing Workshop, Hong Kong, China, Oct. 1-8, 2000, pp.46-51.","DOI":"10.3115\/1117769.1117777"},{"key":"9411_CR9","first-page":"1","volume":"18","author":"G Zou","year":"2004","unstructured":"Zou G., Liu Y., Liu Q. Internet-oriented Chinese New Words Detection (in Chinese). Journal of Chinese Information Processing, 2004, 18: 1-9.","journal-title":"Journal of Chinese Information Processing"},{"key":"9411_CR10","doi-asserted-by":"crossref","unstructured":"Peng F, Feng F, McCallum A. Chinese segmentation and new word detection using conditional random fields. In Proc. the 20th International Conference on Computational Linguistics, Geneva, Switzerland, Aug. 23-27, 2004, pp.562-569.","DOI":"10.3115\/1220355.1220436"},{"key":"9411_CR11","unstructured":"Lafferty J, McCallum A, Pereira F. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proc. the 18th Int. Conf. Machine Learning, Williamstown, USA, Jun. 28-Jul. 1, 2001, pp.282-289."},{"issue":"4","key":"9411_CR12","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1007\/s11390-008-9157-4","volume":"23","author":"H Zhao","year":"2008","unstructured":"Zhao H, Kit C. Scaling conditional random fields by one-against-the-other decomposition. Journal of Computer Science and Technology, July, 2008, 23(4): 612-619.","journal-title":"Journal of Computer Science and Technology, July"},{"key":"9411_CR13","doi-asserted-by":"crossref","unstructured":"Li H Q, Huang C N, Gao J F, Fan X Z. The use of SVM for Chinese new word identification. In Proc. IJCNLP 2004, Sanya, China, Mar. 22-24, 2004, pp.723-732.","DOI":"10.1007\/978-3-540-30211-7_76"},{"key":"9411_CR14","doi-asserted-by":"crossref","unstructured":"Asahara M, Matsumoto Y. Japanese unknown word identification by character-based chunking. In Proc. the 20th International Conference on Computational Linguistics, Geneva, Switzerland, Aug. 23-27, 2004, pp.459-465.","DOI":"10.3115\/1220355.1220421"},{"issue":"1","key":"9411_CR15","first-page":"1","volume":"15","author":"CL Goh","year":"2005","unstructured":"Goh C L, Asahara M, Matsumoto Y. Training multi-classifiers for Chinese unknown word detection. Journal of Chinese Language and Computing, 2005, 15(1): 1-12.","journal-title":"Journal of Chinese Language and Computing"},{"key":"9411_CR16","first-page":"185","volume":"16","author":"G Goh","year":"2006","unstructured":"Goh G, Asahara M, Matsumoto Y. Machine learning-based methods to Chinese unknown word detection and POS tag guessing. Journal of Chinese Language and Computing, 2006, 16: 185-206.","journal-title":"Journal of Chinese Language and Computing"},{"key":"9411_CR17","doi-asserted-by":"crossref","unstructured":"Morency L, Quattoni A, Darrell T. Latent-dynamic discriminative models for continuous gesture recognition. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, USA, Jun. 17-22, 2007, pp.1-8.","DOI":"10.1109\/CVPR.2007.383299"},{"issue":"4","key":"9411_CR18","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1007\/s11390-008-9156-5","volume":"23","author":"X Sun","year":"2008","unstructured":"Sun X, Wang H, Wang B. Predicting Chinese abbreviations from definitions: An empirical learning approach using support vector regression. Journal of Computer Science and Technology, 2008, 23(4): 602-611.","journal-title":"Journal of Computer Science and Technology"},{"key":"9411_CR19","doi-asserted-by":"crossref","unstructured":"Sun X, Huang D, Ren F. Detecting new words from Chinese text using latent semi-CRF models. IEICE Transactions on Information and Systems, 2010, E93-D(6): 1386-1393.","DOI":"10.1587\/transinf.E93.D.1386"},{"key":"9411_CR20","unstructured":"Sarawagi S, Cohen W. Semi-Markov conditional random fields for information extraction. In Proc. NIPS 2004, Vancouver, Canada, Dec. 13-18, 2004, pp.1185-1192."},{"key":"9411_CR21","doi-asserted-by":"crossref","unstructured":"Okanohara D, Miyao Y, Tsuruoka Y, Tsujii J. Improving the scalability of semi-Markov conditional random fields for named entity recognition. In Proc. the 21st Int. Conf. Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Sydney, Australia, Jul. 17-21, 2006, pp.465-472.","DOI":"10.3115\/1220175.1220234"},{"issue":"3","key":"9411_CR22","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1007\/BF01589116","volume":"45","author":"D Liu","year":"1989","unstructured":"Liu D, Nocedal J. On the limited memory BFGS method for large scale optimization. Mathematical Programming, 1989, 45(3): 503-528.","journal-title":"Mathematical Programming"},{"key":"9411_CR23","first-page":"121","volume":"13","author":"S Yu","year":"2003","unstructured":"Yu S, Duan H, Zhu X, Swen B, Chang B. Specification for corpus processing at Peking University: Word segmentation, POS tagging and phonetic notation. Journal of Chinese Language and Computing, 2003, 13: 121-158.","journal-title":"Journal of Chinese Language and Computing"},{"key":"9411_CR24","doi-asserted-by":"crossref","unstructured":"Zhou G. A chunking strategy towards unknown word detection in Chinese word segmentation. In Proc. IJCNLP 2005, Jeju Island, Korea, Oct. 11-13, 2005, pp.530-541.","DOI":"10.1007\/11562214_47"},{"key":"9411_CR25","doi-asserted-by":"crossref","unstructured":"Sproat R, Emerson T. The first international Chinese word segmentation bakeoff. In Proc. the 2nd SIGHAN Workshop on Chinese Language Processing, Sapporo, Japan, Jul. 11-12, 2003, pp.133-143.","DOI":"10.3115\/1119250.1119269"},{"key":"9411_CR26","unstructured":"Emerson T. The second international Chinese word segmentation bakeoff. In Proc. the 4th SIGHAN Workshop on Chinese Language Processing, Jeju Island, Korea, Oct. 14-15, 2005, pp.123-133."},{"key":"9411_CR27","unstructured":"Levow G A. The third international Chinese language processing bakeoff: Word segmentation and named entity recognition. In Proc. the 5th SIGHAN Workshop on Chinese Language Processing, Sydney, Australia, Jul. 22-23, 2006, pp.108-117."},{"key":"9411_CR28","unstructured":"Jin G, Chen X. The fourth international Chinese language processing bakeoff: Chinese word segmentation, named entity recognition and Chinese POS tagging. In Proc. Sixth SIGHAN Workshop on Chinese Language Processing, Hyderabad, India, Jan. 11-12, 2008, pp.69-81."}],"container-title":["Journal of Computer Science and Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11390-011-9411-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11390-011-9411-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11390-011-9411-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T16:01:14Z","timestamp":1740844874000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11390-011-9411-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,1]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2011,1]]}},"alternative-id":["9411"],"URL":"https:\/\/doi.org\/10.1007\/s11390-011-9411-z","relation":{},"ISSN":["1000-9000","1860-4749"],"issn-type":[{"type":"print","value":"1000-9000"},{"type":"electronic","value":"1860-4749"}],"subject":[],"published":{"date-parts":[[2011,1]]}}}