Linguistic Structure PredictionMorgan & Claypool Publishers, 2011 - 248 sayfa A major part of natural language processing now depends on the use of text data to build linguistic analyzers. We consider statistical, computational approaches to modeling linguistic structure. We seek to unify across many approaches and many kinds of linguistic structures. Assuming a basic understanding of natural language processing and/or machine learning, we seek to bridge the gap between the two fields. Approaches to decoding (i.e., carrying out linguistic structure prediction) and supervised and unsupervised learning of models that predict discrete structures as outputs are the focus. We also survey natural language processing problems to which these methods are being applied, and we address related topics in probabilistic inference, optimization, and experimental methodology. Table of Contents: Representations and Linguistic Data / Decoding: Making Predictions / Learning Structure from Annotated Data / Learning Structure from Incomplete Data / Beyond Decoding: Inference |
İçindekiler
| 1 | |
Making Predictions | 23 |
Learning Structure from Annotated Data | 69 |
Learning Structure from Incomplete Data | 109 |
Inference | 147 |
Numerical Optimization | 169 |
Experimentation | 181 |
Maximum Entropy | 199 |
Locally Normalized Conditional Models | 203 |
Bibliography | 209 |
Authors Biography | 241 |
Diğer baskılar - Tümünü görüntüle
Sık kullanılan terimler ve kelime öbekleri
algorithm annotated approach approximate argmax Association for Computational axioms Bayesian calculate chapter Cited on page(s Computational Linguistics conditional models consider constraints context-free corresponds dataset decoding problem defined denote dependency parsing derivation Dirichlet discussed DP equations dynamic programming entropy expwg(x factor figure Gibbs sampling given goal grammar graph graphical models hidden variable Human Language Technologies hypergraph hyperpath inference input iteration linear linguistic structure prediction locally normalized log-linear models logic program loss function machine learning Markov maximizing maximum likelihood estimation methods multinomial distribution Natural Language Processing nonterminal notation null hypothesis objective function output parameters parts(x posterior predictors probabilistic probability Proceedings proof pw(Y random variable reverse value sample semiring sentence sequence labeling solving statistic step tagging techniques theorem training data unsupervised learning update vertex weights wg(x word X₁ ΣΣ