{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T12:03:01Z","timestamp":1759147381291,"version":"3.37.3"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"8-10","license":[{"start":{"date-parts":[[2018,5,22]],"date-time":"2018-05-22T00:00:00Z","timestamp":1526947200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,5,22]],"date-time":"2018-05-22T00:00:00Z","timestamp":1526947200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DE170100037","DP140100087"],"award-info":[{"award-number":["DE170100037","DP140100087"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1007\/s10994-018-5718-0","type":"journal-article","created":{"date-parts":[[2018,5,22]],"date-time":"2018-05-22T17:01:09Z","timestamp":1527008469000},"page":"1303-1331","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Accurate parameter estimation for Bayesian network classifiers using hierarchical Dirichlet processes"],"prefix":"10.1007","volume":"107","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5334-3574","authenticated-orcid":false,"given":"Fran\u00e7ois","family":"Petitjean","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9292-1015","authenticated-orcid":false,"given":"Wray","family":"Buntine","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9963-5169","authenticated-orcid":false,"given":"Geoffrey I.","family":"Webb","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nayyar","family":"Zaidi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,5,22]]},"reference":[{"issue":"1","key":"5718_CR1","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1145\/2576868","volume":"47","author":"C Bielza","year":"2014","unstructured":"Bielza, C., & Larra\u00f1aga, P. (2014). Discrete Bayesian network classifiers: A survey. ACM Computing Surveys, 47(1), 5.","journal-title":"ACM Computing Surveys"},{"issue":"02","key":"5718_CR2","doi-asserted-by":"publisher","first-page":"125,1001","DOI":"10.1142\/S0218001412510019","volume":"26","author":"H Bostr\u00f6m","year":"2012","unstructured":"Bostr\u00f6m, H. (2012). Forests of probability estimation trees. International Journal of Pattern Recognition and Artificial Intelligence, 26(02), 125,1001.","journal-title":"International Journal of Pattern Recognition and Artificial Intelligence"},{"key":"5718_CR3","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. (2001). Random forests. Machine Learning, 45, 5\u201332.","journal-title":"Machine Learning"},{"issue":"2","key":"5718_CR4","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1109\/69.494161","volume":"8","author":"W Buntine","year":"1996","unstructured":"Buntine, W. (1996). A guide to the literature on learning probabilistic networks from data. IEEE Transactions on Knowledge and Data Engineering, 8(2), 195\u2013210.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"5718_CR5","doi-asserted-by":"crossref","unstructured":"Buntine, W., & Mishra, S. (2014). Experiments with non-parametric topic models. In 20th ACM SIGKDD international conference on knowledge discovery and data Mining, ACM, New York, NY, USA, KDD \u201914 (pp. 881\u2013890).","DOI":"10.1145\/2623330.2623691"},{"issue":"July","key":"5718_CR6","first-page":"2181","volume":"12","author":"AM Carvalho","year":"2011","unstructured":"Carvalho, A. M., Roos, T., Oliveira, A. L., & Myllym\u00e4ki, P. (2011). Discriminative learning of Bayesian networks via factorized conditional log-likelihood. Journal of Machine Learning Research, 12(July), 2181\u20132210.","journal-title":"Journal of Machine Learning Research"},{"key":"5718_CR7","doi-asserted-by":"crossref","unstructured":"Chen, S., & Goodman, J. (1996). An empirical study of smoothing techniques for language modeling. In 34th Annual meeting on association for computational linguistics, ACL \u201996 (pp. 310\u2013318).","DOI":"10.3115\/981863.981904"},{"key":"5718_CR8","doi-asserted-by":"publisher","unstructured":"Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, ACM, New York, NY, USA, KDD \u201916 (pp. 785\u2013794). \n                    https:\/\/doi.org\/10.1145\/2939672.2939785\n                    \n                  .","DOI":"10.1145\/2939672.2939785"},{"issue":"3","key":"5718_CR9","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1109\/TIT.1968.1054142","volume":"14","author":"C Chow","year":"1968","unstructured":"Chow, C., & Liu, C. (1968). Approximating discrete probability distributions with dependence trees. IEEE Transactions on Information Theory, 14(3), 462\u2013467.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"1","key":"5718_CR10","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s10994-010-5197-4","volume":"81","author":"L Du","year":"2010","unstructured":"Du, L., Buntine, W., & Jin, H. (2010). A segmented topic model based on the two-parameter Poisson\u2013Dirichlet process. Machine Learning, 81(1), 5\u201319.","journal-title":"Machine Learning"},{"issue":"1","key":"5718_CR11","first-page":"87","volume":"8","author":"U Fayyad","year":"1992","unstructured":"Fayyad, U., & Irani, K. (1992). On the handling of continuous-valued attributes in decision tree generation. Machine Learning, 8(1), 87\u2013102.","journal-title":"Machine Learning"},{"key":"5718_CR12","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1214\/aos\/1176342360","volume":"1","author":"T Ferguson","year":"1973","unstructured":"Ferguson, T. (1973). A Bayesian analysis of some nonparametric problems. The Annals of Statistics, 1, 209\u2013230.","journal-title":"The Annals of Statistics"},{"issue":"2","key":"5718_CR13","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1023\/A:1007465528199","volume":"29","author":"N Friedman","year":"1997","unstructured":"Friedman, N., Geiger, D., & Goldszmidt, M. (1997). Bayesian network classifiers. Machine Learning, 29(2), 131\u2013163.","journal-title":"Machine Learning"},{"issue":"1\u20132","key":"5718_CR14","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1023\/A:1020249912095","volume":"50","author":"N Friedman","year":"2003","unstructured":"Friedman, N., & Koller, D. (2003). Being Bayesian about network structure. A Bayesian approach to structure discovery in Bayesian networks. Machine Learning, 50(1\u20132), 95\u2013125.","journal-title":"Machine Learning"},{"key":"5718_CR15","unstructured":"Gasthaus, J., & Teh, Y. (2010). Improvements to the sequence memoizer. In: J.D. Lafferty, C.K.I. Williams, J. Shawe-Taylor, R.S. Zemel, & A. Culotta, Proceedings of the 23rd International Conference on Neural Information Processing Systems NIPS\u201910, Vancouver, British Columbia, Canada, 6\u20139 December 2010 (Vol. 1, pp. 685\u2013693). Curran Associates Inc."},{"key":"5718_CR16","unstructured":"Hardy, G. H. [(1889) 1920]. Letter. Transactions of the Faculty of Actuaries 8, pp. 180\u2013181 (originally published on \u201cInsurance Record 457\u201d)."},{"key":"5718_CR17","unstructured":"Huynh, V., Phung, D. Q., Venkatesh, S., Nguyen, X., Hoffman, M. D., & Bui, H. H. (2016). Scalable nonparametric Bayesian multilevel clustering. In UAI."},{"issue":"2","key":"5718_CR18","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1016\/0097-3165(95)90010-1","volume":"71","author":"HK Hwang","year":"1995","unstructured":"Hwang, H. K. (1995). Asymptotic expansions for the Stirling numbers of the first kind. Journal of Combinatorial Theory, Series A, 71(2), 343\u2013351.","journal-title":"Journal of Combinatorial Theory, Series A"},{"key":"5718_CR19","volume-title":"Probabilistic graphical models\u2014Principles and techniques. Adaptive computation and machine learning","author":"D Koller","year":"2009","unstructured":"Koller, D., & Friedman, N. (2009). Probabilistic graphical models\u2014Principles and techniques. Adaptive computation and machine learning. Cambridge, MA: The MIT Press."},{"key":"5718_CR20","doi-asserted-by":"crossref","unstructured":"Lewis, D. (1998). Naive Bayes at forty: The independence assumption in information retrieval. In 10th European conference on machine learning, Springer, London, UK, ECML \u201998 (pp. 4\u201315).","DOI":"10.1007\/BFb0026666"},{"key":"5718_CR21","unstructured":"Lichman, M. (2013). UCI machine learning repository. \n                    http:\/\/archive.ics.uci.edu\/ml\n                    \n                   Accessed 23 Jan 2015."},{"key":"5718_CR22","first-page":"182","volume":"8","author":"G Lidstone","year":"1920","unstructured":"Lidstone, G. (1920). Note on the general case of the Bayes\u2013Laplace formula for inductive or a posteriori probabilities. Transactions of the Faculty Actuaries, 8, 182\u2013192.","journal-title":"Transactions of the Faculty Actuaries"},{"key":"5718_CR23","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/j.ijar.2016.07.007","volume":"78","author":"K Lim","year":"2016","unstructured":"Lim, K., Buntine, W., Chen, C., & Du, L. (2016). Nonparametric Bayesian topic modelling with the hierarchical Pitman\u2013Yor processes. International Journal of Approximate Reasoning, 78, 172\u2013191.","journal-title":"International Journal of Approximate Reasoning"},{"key":"5718_CR24","volume-title":"Apache Mahout: Beyond MapReduce","author":"D Lyubimov","year":"2016","unstructured":"Lyubimov, D., & Palumbo, A. (2016). Apache Mahout: Beyond MapReduce (1st ed.). North Charleston: CreateSpace Independent Publishing Platform.","edition":"1"},{"issue":"44","key":"5718_CR25","first-page":"1","volume":"17","author":"A Mart\u00ednez","year":"2016","unstructured":"Mart\u00ednez, A., Webb, G., Chen, S., & Zaidi, N. (2016). Scalable learning of Bayesian network classifiers. Journal of Machine Learning Research, 17(44), 1\u201335.","journal-title":"Journal of Machine Learning Research"},{"key":"5718_CR26","volume-title":"Machine learning","author":"T Mitchell","year":"1997","unstructured":"Mitchell, T. (1997). Machine learning. New York: McGraw-Hill."},{"key":"5718_CR27","doi-asserted-by":"crossref","unstructured":"Nguyen, V., Phung, D. Q., Venkatesh, S., & Bui, H. H. (2015). A Bayesian nonparametric approach to multilevel regression. In PAKDD (Vol. 1, pp. 330\u2013342).","DOI":"10.1007\/978-3-319-18038-0_26"},{"key":"5718_CR28","unstructured":"Rennie, J., Shih, L., Teevan, J., & Karger, D. (2003). Tackling the poor assumptions of naive Bayes text classifiers. In 20th International conference on machine learning, AAAI Press, ICML\u201903 (pp. 616\u2013623)."},{"issue":"3","key":"5718_CR29","first-page":"267","volume":"59","author":"T Roos","year":"2005","unstructured":"Roos, T., Wettig, H., Gr\u00fcnwald, P., Myllym\u00e4ki, P., & Tirri, H. (2005). On discriminative Bayesian network classifiers and logistic regression. Machine Learning, 59(3), 267\u2013296.","journal-title":"Machine Learning"},{"key":"5718_CR30","unstructured":"Sahami, M. (1996). Learning limited dependence Bayesian classifiers. In Second international conference on knowledge discovery and data mining (pp. 334\u2013338). AAAI Press, Menlo Park, CA."},{"key":"5718_CR31","doi-asserted-by":"crossref","unstructured":"Shareghi, E., Cohn, T., & Haffari, G. (2016). Richer interpolative smoothing based on modified Kneser-Ney language modeling. In Empirical methods in natural language processing (pp. 944\u2013949).","DOI":"10.18653\/v1\/D16-1094"},{"key":"5718_CR32","doi-asserted-by":"crossref","unstructured":"Shareghi, E., Haffari, G., & Cohn, T. (2017a). Compressed nonparametric language modelling. In IJCAI. Accepted 23\/04\/2017.","DOI":"10.24963\/ijcai.2017\/376"},{"key":"5718_CR33","doi-asserted-by":"publisher","unstructured":"Shareghi, E., Haffari, G., & Cohn, T. (2017b). Compressed nonparametric language modelling. In Proceedings of the twenty-sixth international joint conference on artificial intelligence, IJCAI-17 (pp. 2701\u20132707). \n                    https:\/\/doi.org\/10.24963\/ijcai.2017\/376\n                    \n                  .","DOI":"10.24963\/ijcai.2017\/376"},{"key":"5718_CR34","unstructured":"Sonnenburg, S., & Franc, V. (2010). COFFIN: A computational framework for linear SVMs. In J. F\u00fcrnkranz & T. Joachims (Eds.), ICML (pp. 999\u20131006)."},{"key":"5718_CR35","unstructured":"Teh, Y. (2006). A Bayesian interpretation of interpolated Kneser-Ney. Tech. Rep. TRA2\/06, School of Computing, National University of Singapore."},{"issue":"476","key":"5718_CR36","doi-asserted-by":"publisher","first-page":"1566","DOI":"10.1198\/016214506000000302","volume":"101","author":"Y Teh","year":"2006","unstructured":"Teh, Y., Jordan, M., Beal, M., & Blei, D. (2006). Hierarchical Dirichlet processes. Journal of the American Statistical Association, 101(476), 1566\u20131581.","journal-title":"Journal of the American Statistical Association"},{"issue":"1","key":"5718_CR37","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s10994-005-4258-6","volume":"58","author":"GI Webb","year":"2005","unstructured":"Webb, G. I., Boughton, J., & Wang, Z. (2005). Not so naive Bayes: Aggregating one-dependence estimators. Machine Learning, 58(1), 5\u201324.","journal-title":"Machine Learning"},{"issue":"2","key":"5718_CR38","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/s10994-011-5263-6","volume":"86","author":"G Webb","year":"2012","unstructured":"Webb, G., Boughton, J., Zheng, F., Ting, K., & Salem, H. (2012). Learning by extrapolation from marginal to full-multivariate probability distributions: Decreasingly naive Bayesian classification. Machine Learning, 86(2), 233\u2013272.","journal-title":"Machine Learning"},{"issue":"3","key":"5718_CR39","doi-asserted-by":"publisher","first-page":"537","DOI":"10.2307\/2336490","volume":"70","author":"N Wermuth","year":"1983","unstructured":"Wermuth, N., & Lauritzen, S. (1983). Graphical and recursive models for contigency tables. Biometrika, 70(3), 537\u2013552.","journal-title":"Biometrika"},{"issue":"2","key":"5718_CR40","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1145\/1897816.1897842","volume":"54","author":"F Wood","year":"2011","unstructured":"Wood, F., Gasthaus, J., Archambeau, C., James, L., & Teh, Y. (2011). The sequence memoizer. Communications of the ACM, 54(2), 91\u201398.","journal-title":"Communications of the ACM"},{"issue":"9\u201310","key":"5718_CR41","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1007\/s10994-016-5619-z","volume":"106","author":"NA Zaidi","year":"2017","unstructured":"Zaidi, N. A., Webb, G. I., Carman, M. J., Petitjean, F., Buntine, W., Hynes, M., et al. (2017). Efficient parameter learning of Bayesian network classifiers. Machine Learning, 106(9\u201310), 1289\u20131329.","journal-title":"Machine Learning"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-018-5718-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-018-5718-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-018-5718-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,17]],"date-time":"2020-05-17T08:09:43Z","timestamp":1589702983000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-018-5718-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,22]]},"references-count":41,"journal-issue":{"issue":"8-10","published-print":{"date-parts":[[2018,9]]}},"alternative-id":["5718"],"URL":"https:\/\/doi.org\/10.1007\/s10994-018-5718-0","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2018,5,22]]},"assertion":[{"value":"28 August 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}