Results 1 - 10 of 2,552

Discriminative Training and Maximum Entropy Models for Statistical Machine Translation

by Franz Josef Och, Hermann Ney , 2002
"... We present a framework for statistical machine translation of natural languages based on direct maximum entropy models, which contains the widely used source -channel approach as a special case. All knowledge sources are treated as feature functions, which depend on the source language senten ..."
Abstract - Cited by 508 (30 self) - Add to MetaCart
We present a framework for statistical machine translation of natural languages based on direct maximum entropy models, which contains the widely used source -channel approach as a special case. All knowledge sources are treated as feature functions, which depend on the source language

The TSIMMIS Project: Integration of Heterogeneous Information Sources

by Sudarshan Chawathe, Hector Garcia-Molina, Joachim Hammer, Kelly Ireland, Yannis Papakonstantinou, Jeffrey Ullman, Jennifer Widom
"... The goal of the Tsimmis Project is to develop tools that facilitate the rapid integration of heterogeneous information sources that may include both structured and unstructured data. This paper gives an overview of the project, describing components that extract properties from unstructured objects, ..."
Abstract - Cited by 535 (19 self) - Add to MetaCart
, that translate information into a common object model, that combine information from several sources, that allow browsing of information, and that manage constraints across heterogeneous sites. Tsimmis is a joint project between Stanford and the IBM Almaden Research Center.

The Alignment Template Approach to Statistical Machine Translation

by Franz Josef Och, Hermann Ney , 2004
"... A phrase-based statistical machine translation approach — the alignment template approach — is described. This translation approach allows for general many-to-many relations between words. Thereby, the context of words is taken into account in the translation model, and local changes in word order f ..."
Abstract - Cited by 480 (26 self) - Add to MetaCart
from source to target language can be learned explicitly. The model is described using a log-linear modeling approach, which is a generalization of the often used source–channel approach. Thereby, the model is easier to extend than classical statistical machine translation systems. We describe

What is a hidden Markov model?

by Sean R. Eddy , 2004
"... Often, problems in biological sequence analysis are just a matter of putting the right label on each residue. In gene identification, we want to label nucleotides as exons, introns, or intergenic sequence. In sequence alignment, we want to associate residues in a query sequence with ho-mologous resi ..."
Abstract - Cited by 1344 (8 self) - Add to MetaCart
-mologous residues in a target database sequence. We can always write an ad hoc program for any given problem, but the same potentially frustrating issues will always recur. One issue is that we often want to incorporate multiple heterogenous sources of information. A genefinder, for in-stance, ought to combine

Pattern-based model-to-model transformation

by Juan De Lara, Esther Guerra - In Proc. ICGT’08, volume 5214 of LNCS , 2008
"... Abstract. We present a new, high-level approach for the specification of model-to-model transformations based on declarative patterns. These are (atomic or composite) constraints on triple graphs declaring the allowed or forbidden relationships between source and target models. In this way, a transf ..."
Abstract - Cited by 18 (7 self) - Add to MetaCart
Abstract. We present a new, high-level approach for the specification of model-to-model transformations based on declarative patterns. These are (atomic or composite) constraints on triple graphs declaring the allowed or forbidden relationships between source and target models. In this way, a

A Syntax-based Statistical Translation Model

by Kenji Yamada, Kevin Knight , 2001
"... We present a syntax-based statistical translation model. Our model transforms a source-language parse tree into a target-language string by applying stochastic operations at each node. These operations capture linguistic differences such as word order and case marking. Model parameters are es ..."
Abstract - Cited by 343 (16 self) - Add to MetaCart
We present a syntax-based statistical translation model. Our model transforms a source-language parse tree into a target-language string by applying stochastic operations at each node. These operations capture linguistic differences such as word order and case marking. Model parameters

G.: Model-to-Model Transformations By Demonstration

by Philip Langer, Tu Wien, Philip Langer, Manuel Wimmer - In: Proc. 3rd International Conference on Model Transformation (ICMT’10 , 2010
"... Abstract. During the last decade several approaches have been pro-posed for easing the burden of writing model transformation rules manu-ally. Among them are Model Transformation By-Demonstration (MTBD) approaches which record actions performed on example models to derive general operations. A curre ..."
Abstract - Cited by 4 (2 self) - Add to MetaCart
current restriction of MTBD is that until now they are only available for in-place transformations, but not for model-to-model (M2M) transformations. In this paper, we extend our MTBD approach, which is designed for in-place transformations, to also support M2M transformations. In partic-ular, we propose

Translating Web Data

by Lucian Popa, Yannis Velegrakis, Renee J. Miller, Mauricio A. Hernandez, Ronald Fagin - In VLDB , 2002
"... We present a novel framework for mapping between any combination of XML and relational schemas, in which a high-level, userspecified mapping is translated into semantically meaningful queries that transform source data into the target representation. Our approach works in two phases. In the first ph ..."
Abstract - Cited by 229 (40 self) - Add to MetaCart
We present a novel framework for mapping between any combination of XML and relational schemas, in which a high-level, userspecified mapping is translated into semantically meaningful queries that transform source data into the target representation. Our approach works in two phases. In the first

An Invariant-Based Method for the Analysis of Declarative Model-to-Model Transformations

by Jordi Cabot, Esther Guerra, Juan De Lara
"... Abstract. In this paper we propose a method to derive OCL invariants from declarative specifications of model-to-model transformations. In particular we consider two of the most prominent approaches for specifying such transformations: Triple Graph Grammars and QVT. Once the specification is express ..."
Abstract - Cited by 4 (1 self) - Add to MetaCart
Abstract. In this paper we propose a method to derive OCL invariants from declarative specifications of model-to-model transformations. In particular we consider two of the most prominent approaches for specifying such transformations: Triple Graph Grammars and QVT. Once the specification

Using Schema Matching to Simplify Heterogeneous Data Translation

by Tova Milo, Sagit Zohar , 1998
"... A broad spectrum of data is available on the Web in distinct heterogeneous sources, and stored under different formats. As the number of systems that utilize this heterogeneous data grows, the importance of data translation and conversion mechanisms increases greatly. In this paper we present a n ..."
Abstract - Cited by 252 (5 self) - Add to MetaCart
new translation system, based on schemamatching, aimed to simplify the intricate task of data conversion. We observe that in many cases the schema of the data in the source system is very similar to the that of the target system. In such cases, much of the translation work can be done automatically
Results 1 - 10 of 2,552