@inproceedings{lafferty2001conditional, acmid = {655813}, address = {San Francisco, CA, USA}, author = {Lafferty, John D. and McCallum, Andrew and Pereira, Fernando C. N.}, booktitle = {Proceedings of the Eighteenth International Conference on Machine Learning}, interhash = {574c59001ecc3aa04850e1751d96c137}, intrahash = {180c5d6097317fa1b19ca8df75341230}, isbn = {1-55860-778-1}, numpages = {8}, pages = {282--289}, publisher = {Morgan Kaufmann Publishers Inc.}, title = {Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data}, url = {http://dl.acm.org/citation.cfm?id=645530.655813}, year = 2001 } @inproceedings{kristjansson2004interactive, abstract = {Information Extraction methods can be used to automatically "fill-in" database forms from unstructured data such as Web documents or email. State-of-the-art methods have achieved low error rates but invariably make a number of errors. The goal of an interactive information extraction system is to assist the user in filling in database fields while giving the user confidence in the integrity of the data. The user is presented with an interactive interface that allows both the rapid verification of automatic field assignments and the correction of errors. In cases where there are multiple errors, our system takes into account user corrections, and immediately propagates these constraints such that other fields are often corrected automatically. Linear-chain conditional random fields (CRFs) have been shown to perform well for information extraction and other language modelling tasks due to their ability to capture arbitrary, overlapping features of the input in aMarkov model. We apply this framework with two extensions: a constrained Viterbi decoding which finds the optimal field assignments consistent with the fields explicitly specified or corrected by the user; and a mechanism for estimating the confidence of each extracted field, so that low-confidence extractions can be highlighted. Both of these mechanisms are incorporated in a novel user interface for form filling that is intuitive and speeds the entry of data—providing a 23% reduction in error due to automated corrections.}, author = {Kristjansson, Trausti T. and Culotta, Aron and Viola, Paul A. and McCallum, Andrew}, booktitle = {AAAI}, editor = {McGuinness, Deborah L. and Ferguson, George}, interhash = {89fe7fe6ef4c088b10d3b0b0aabeaf46}, intrahash = {fe6cb1dbef3216852a63a625a30799d6}, isbn = {0-262-51183-5}, pages = {412--418}, publisher = {AAAI Press/The MIT Press}, title = {Interactive Information Extraction with Constrained Conditional Random Fields.}, url = {http://dblp.uni-trier.de/db/conf/aaai/aaai2004.html#KristjanssonCVM04}, year = 2004 } @misc{sutton2010introduction, abstract = { Often we wish to predict a large number of variables that depend on each other as well as on other observed variables. Structured prediction methods are essentially a combination of classification and graphical modeling, combining the ability of graphical models to compactly model multivariate data with the ability of classification methods to perform prediction using large sets of input features. This tutorial describes conditional random fields, a popular probabilistic method for structured prediction. CRFs have seen wide application in natural language processing, computer vision, and bioinformatics. We describe methods for inference and parameter estimation for CRFs, including practical issues for implementing large scale CRFs. We do not assume previous knowledge of graphical modeling, so this tutorial is intended to be useful to practitioners in a wide variety of fields. }, author = {Sutton, Charles and McCallum, Andrew}, interhash = {05e1b6859124c5bf51c7aafd63f779b0}, intrahash = {49d8c9beb76a8b88739aa9eece7446ee}, note = {cite arxiv:1011.4088Comment: 90 pages}, title = {An Introduction to Conditional Random Fields}, url = {http://arxiv.org/abs/1011.4088}, year = 2010 } @misc{Sutton2010, abstract = { Often we wish to predict a large number of variables that depend on each other as well as on other observed variables. Structured prediction methods are essentially a combination of classification and graphical modeling, combining the ability of graphical models to compactly model multivariate data with the ability of classification methods to perform prediction using large sets of input features. This tutorial describes conditional random fields, a popular probabilistic method for structured prediction. CRFs have seen wide application in natural language processing, computer vision, and bioinformatics. We describe methods for inference and parameter estimation for CRFs, including practical issues for implementing large scale CRFs. We do not assume previous knowledge of graphical modeling, so this tutorial is intended to be useful to practitioners in a wide variety of fields. }, author = {Sutton, Charles and McCallum, Andrew}, interhash = {05e1b6859124c5bf51c7aafd63f779b0}, intrahash = {49d8c9beb76a8b88739aa9eece7446ee}, note = {cite arxiv:1011.4088Comment: 90 pages}, title = {An Introduction to Conditional Random Fields}, url = {http://arxiv.org/abs/1011.4088}, year = 2010 } @inproceedings{bekkerman2005multiway, abstract = {We present a novel unsupervised learning scheme that simultaneously clusters variables of several types (e.g., documents, words and authors) based on pairwise interactions between the types, as observed in co-occurrence data. In this scheme, multiple clustering systems are generated aiming at maximizing an objective function that measures multiple pairwise mutual information between cluster variables. To implement this idea, we propose an algorithm that interleaves top-down clustering of some variables and bottom-up clustering of the other variables, with a local optimization correction routine. Focusing on document clustering we present an extensive empirical study of two-way, three-way and four-way applications of our scheme using six real-world datasets including the 20 News-groups (20NG) and the Enron email collection. Our multi-way distributional clustering (MDC) algorithms consistently and significantly outperform previous state-of-the-art information theoretic clustering algorithms.}, address = {New York, NY, USA}, author = {Bekkerman, Ron and El-Yaniv, Ran and McCallum, Andrew}, booktitle = {ICML '05: Proceedings of the 22nd International Conference on Machine learning}, doi = {10.1145/1102351.1102357}, interhash = {25609f84a6916c1664e61d8618f46a32}, intrahash = {2921f89f8663e7bcc122a2a77c66e7c2}, isbn = {1-59593-180-5}, location = {Bonn, Germany}, pages = {41--48}, publisher = {ACM}, title = {Multi-way distributional clustering via pairwise interactions}, url = {http://portal.acm.org/citation.cfm?id=1102351.1102357}, year = 2005 } @inproceedings{1102357, address = {New York, NY, USA}, author = {Bekkerman, Ron and El-Yaniv, Ran and McCallum, Andrew}, booktitle = {ICML '05: Proceedings of the 22nd international conference on Machine learning}, doi = {http://doi.acm.org/10.1145/1102351.1102357}, interhash = {25609f84a6916c1664e61d8618f46a32}, intrahash = {a5ac489feb7407a07570f6733665a6dd}, isbn = {1-59593-180-5}, location = {Bonn, Germany}, pages = {41--48}, publisher = {ACM Press}, title = {Multi-way distributional clustering via pairwise interactions}, url = {http://www.cs.technion.ac.il/~rani/el-yaniv-papers/BekkermanEM05.pdf}, year = 2005 } @inproceedings{baker98distributional, address = {Melbourne, AU}, author = {Baker, L. Douglas and McCallum, Andrew K.}, booktitle = {Proceedings of {SIGIR}-98, 21st {ACM} International Conference on Research and Development in Information Retrieval}, editor = {Croft, W. Bruce and Moffat, Alistair and van Rijsbergen, Cornelis J. and Wilkinson, Ross and Zobel, Justin}, interhash = {f116fa6b3ef1eefecb8bf27dfaa53ee7}, intrahash = {e472dc4e61921ed15175756fcd9fea6a}, pages = {96--103}, publisher = {ACM Press, New York, US}, title = {Distributional clustering of words for text classification}, url = {citeseer.ist.psu.edu/baker98distributional.html}, year = 1998 } @inproceedings{pm04accurate, author = {Peng, Fuchun and McCallum, Andrew}, booktitle = {HLT-NAACL}, ee = {http://acl.ldc.upenn.edu/hlt-naacl2004/main/pdf/176_Paper.pdf}, interhash = {8f9ef6b359fef3bd08bfed653fe1bb55}, intrahash = {8d04bc19e470fe4b98e15a27a1e6e7e9}, pages = {329-336}, title = {Accurate Information Extraction from Research Papers using Conditional Random Fields}, url = {http://www.cs.umass.edu/~mccallum/papers/hlt2004.pdf}, year = 2004 } @inproceedings{peng2004accurate, author = {Peng, Fuchun and McCallum, Andrew}, booktitle = {HLT-NAACL}, interhash = {8f9ef6b359fef3bd08bfed653fe1bb55}, intrahash = {8d04bc19e470fe4b98e15a27a1e6e7e9}, pages = {329--336}, title = {Accurate Information Extraction from Research Papers using Conditional Random Fields}, url = {http://acl.ldc.upenn.edu/hlt-naacl2004/main/pdf/176_Paper.pdf}, year = 2004 } @unpublished{McCallumMALLET, author = {McCallum, Andrew Kachites}, interhash = {a41946adb992cd2c89158609adc0d83f}, intrahash = {6dbb7b45a3a53997359a5e3c2677dc52}, note = {http://mallet.cs.umass.edu}, title = {{MALLET: A Machine Learning for Language Toolkit}}, url = {http://mallet.cs.umass.edu}, year = 2002 }