Results 1 - 10 of 15,525

Minimum Error Rate Training in Statistical Machine Translation

by Franz Josef Och , 2003
"... Often, the training procedure for statistical machine translation models is based on maximum likelihood or related criteria. A general problem of this approach is that there is only a loose relation to the final translation quality on unseen text. In this paper, we analyze various training cri ..."
Abstract - Cited by 757 (7 self) - Add to MetaCart
Often, the training procedure for statistical machine translation models is based on maximum likelihood or related criteria. A general problem of this approach is that there is only a loose relation to the final translation quality on unseen text. In this paper, we analyze various training

Automatic labeling of semantic roles

by Daniel Gildea - Computational Linguistics , 2002
"... We present a system for identifying the semantic relationships, or semantic roles, filled by constituents of a sentence within a semantic frame. Various lexical and syntactic features are derived from parse trees and used to derive statistical classifiers from hand-annotated training data. 1 ..."
Abstract - Cited by 747 (15 self) - Add to MetaCart
We present a system for identifying the semantic relationships, or semantic roles, filled by constituents of a sentence within a semantic frame. Various lexical and syntactic features are derived from parse trees and used to derive statistical classifiers from hand-annotated training data. 1

Gradient-based learning applied to document recognition

by Yann Lecun, Léon Bottou, Yoshua Bengio, Patrick Haffner - Proceedings of the IEEE , 1998
"... Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradientbased learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify hi ..."
Abstract - Cited by 1533 (84 self) - Add to MetaCart
Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradientbased learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify

A Survey of Program Slicing Techniques

by F. Tip - JOURNAL OF PROGRAMMING LANGUAGES , 1995
"... A program slice consists of the parts of a program that (potentially) affect the values computed at some point of interest, referred to as a slicing criterion. The task of computing program slices is called program slicing. The original definition of a program slice was presented by Weiser in 197 ..."
Abstract - Cited by 790 (10 self) - Add to MetaCart
A program slice consists of the parts of a program that (potentially) affect the values computed at some point of interest, referred to as a slicing criterion. The task of computing program slices is called program slicing. The original definition of a program slice was presented by Weiser

Improved Boosting Algorithms Using Confidence-rated Predictions

by Robert E. Schapire , Yoram Singer - MACHINE LEARNING , 1999
"... We describe several improvements to Freund and Schapire’s AdaBoost boosting algorithm, particularly in a setting in which hypotheses may assign confidences to each of their predictions. We give a simplified analysis of AdaBoost in this setting, and we show how this analysis can be used to find impr ..."
Abstract - Cited by 940 (26 self) - Add to MetaCart
improved parameter settings as well as a refined criterion for training weak hypotheses. We give a specific method for assigning confidences to the predictions of decision trees, a method closely related to one used by Quinlan. This method also suggests a technique for growing decision trees which turns

The Proposition Bank: An Annotated Corpus of Semantic Roles

by Martha Palmer, Paul Kingsbury, Daniel Gildea - Computational Linguistics , 2005
"... The Proposition Bank project takes a practical approach to semantic representation, adding a layer of predicate-argument information, or semantic role labels, to the syntactic structures of the Penn Treebank. The resulting resource can be thought of as shallow, in that it does not represent corefere ..."
Abstract - Cited by 556 (22 self) - Add to MetaCart
and to analyze the frequency of syntactic/semantic alternations in the corpus. We describe an automatic system for semantic role tagging trained on the corpus and discuss the effect on its performance of various types of information, including a comparison of full syntactic parsing with a flat representation

The Vocabulary Problem in Human-System Communication

by G. W. Furnas, T. K. Landauer, L. M. Gomez, S. T. Dumais - COMMUNICATIONS OF THE ACM , 1987
"... In almost all computer applications, users must enter correct words for the desired objects or actions. For success without extensive training, or in first-tries for new targets, the system must recognize terms that will be chosen spontaneously. We studied spontaneous word choice for objects in five ..."
Abstract - Cited by 562 (8 self) - Add to MetaCart
In almost all computer applications, users must enter correct words for the desired objects or actions. For success without extensive training, or in first-tries for new targets, the system must recognize terms that will be chosen spontaneously. We studied spontaneous word choice for objects

Comprehensive database for facial expression analysis

by Takeo Kanade, Jeffrey F. Cohn, Yingli Tian - in Proceedings of Fourth IEEE International Conference on Automatic Face and Gesture Recognition
"... Within the past decade, significant effort has occurred in developing methods of facial expression analysis. Because most investigators have used relatively limited data sets, the generalizability of these various methods remains unknown. We describe the problem space for facial expression analysis, ..."
Abstract - Cited by 593 (51 self) - Add to MetaCart
Within the past decade, significant effort has occurred in developing methods of facial expression analysis. Because most investigators have used relatively limited data sets, the generalizability of these various methods remains unknown. We describe the problem space for facial expression analysis

Statistical pattern recognition: A review

by Anil K. Jain, Robert P. W. Duin, Jianchang Mao - IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , 2000
"... The primary goal of pattern recognition is supervised or unsupervised classification. Among the various frameworks in which pattern recognition has been traditionally formulated, the statistical approach has been most intensively studied and used in practice. More recently, neural network techniques ..."
Abstract - Cited by 1035 (30 self) - Add to MetaCart
The primary goal of pattern recognition is supervised or unsupervised classification. Among the various frameworks in which pattern recognition has been traditionally formulated, the statistical approach has been most intensively studied and used in practice. More recently, neural network

On the algorithmic implementation of multi-class kernel-based vector machines

by Koby Crammer, Yoram Singer, Nello Cristianini, John Shawe-taylor, Bob Williamson - Journal of Machine Learning Research
"... In this paper we describe the algorithmic implementation of multiclass kernel-based vector machines. Our starting point is a generalized notion of the margin to multiclass problems. Using this notion we cast multiclass categorization problems as a constrained optimization problem with a quadratic ob ..."
Abstract - Cited by 559 (13 self) - Add to MetaCart
objective function. Unlike most of previous approaches which typically decompose a multiclass problem into multiple independent binary classification tasks, our notion of margin yields a direct method for training multiclass predictors. By using the dual of the optimization problem we are able
Results 1 - 10 of 15,525