Maximum Entropy Markov Models for Information Extraction and Segmentation

By Andrew McCallum, Dayne Freitag, Fernando C Pereira. International Conference on Machine Learning, 2000

1,657 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/bece46ed303f8eaef2affae2cba4e0aef51fe636

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Machine learning for Internet of Things data analysis: A survey (2017, methodology): “In addition, sequential time series and sequential data exists in many real-world applications, including speech recognition [135], handwriting recognition [136], musical score following [137], and information extraction [134].”
Bidirectional LSTM-CRF Models for Sequence Tagging (2015, methodology): “The work of maximum entropy classiﬁer (Ratnaparkhi, 1996) and Maximum entropy Markov models (MEMMs) (McCallum et al., 2000) fall in this category.”
Conditional Random Fields: An Introduction (2004, background): “The task of assigning label sequences to a set of observation sequences arises in many fields, including bioinformatics, computational linguistics and speech recognition [6, 9, 12].”
Unstructured human activity detection from RGBD images (2011, methodology): “We train a two-layered maximum-entropy Markov model which will capture different properties of human activities, including their hierarchical nature and the transitions between sub-activities over time.”
Hidden Markov Support Vector Machines (2003, methodology): “Our work continues a recent line of research that includes Maximum Entropy Markov Models (MEMMs) (McCallum et al., 2000; Punyakanok & Roth, 2001), Conditional Random Fields (CRFs) (Lafferty et al.”
Toward Optimal Active Learning through Monte Carlo Estimation of Error Reduction (2001, background): “Naive Bayes is not always the best performing classification algorithm for text (McCallum et al., 2000; Joachims, 1998), but it continues to be widely used for the purpose because it is efficient and simple to implement, and even against significantly more complex methods, it rarely trails far…”
Improved Part-of-Speech Tagging for Online Conversational Text with Word Clusters (2013, methodology): “Our tagging model is a first-order maximum entropy Markov model (MEMM), a discriminative sequence model for which training and decoding are extremely efficient (Ratnaparkhi, 1996; McCallum et al., 2000).”
HEADS: Headline Generation as Sequence Prediction Using an Abstract Feature-Rich Space (2015, background): “Some of the most popular proposals are Hidden Markov Models (Rabiner and Juang, 1986), local log-linear classifiers, Maximum Entropy Markov Models (McCallum et al., 2000), and Conditional Random Fields (Lafferty et al.”
Conditional Random Fields for Object Recognition (2004, methodology): “This has led to research on discriminative models for sequence labeling such as MEMM’s [7, 5] and conditional random fields (CRFs)[3].”
Inferring social ties across heterogenous networks (2012, methodology): “Such a feature definition is often used in Conditional Random Fields [17] and Maximum Entropy model [23].”
Efficient Training of Conditional Random Fields (2002, methodology): “[33] performed a number of experiments involving the segmentation of Usenet multipart FAQs.”
Neural conditional random fields (2010, methodology): “A more direct approach is to design a discriminative graphical model that models the conditional distribution P (Y|X) instead of modeling the joint probability as in generative model (Mccallum et al., 2000; Lafferty, 2001).”
Domain Adaptation for Statistical Classifiers (2006, methodology): “We use the standard Begin/In/Out encoding and use a maximum entropy Markov model to perform the tagging (McCallum et al., 2000).”
Encoding linear models as weighted finite-state transducers (2014, methodology): “For example, linear models, such as Maximum Entropy Markov models [4], conditional random ﬁelds (CRF) [5], or the structured perceptron algorithm [6], combine evidence from multiple, typically overlapping, features deﬁned over input/output string pairs (e.g., words and their POS-tags).”
Joint and Conditional Estimation of Tagging and Parsing Models (2001, methodology): “Well-known computational linguistic models such as Maximum-Entropy Markov Models (McCallum et al., 2000) and Stochastic Uniﬁcation-based Grammars (Johnson et al., 1999) are standardly estimated with conditional estimators, and it would be interesting to know whether conditional estimation affects th”
Bidirectional RNN for Medical Event Detection in Electronic Health Records (2016, unknown): “, 2000), and Max-entropy Markov Models (McCallum et al., 2000).”