Results 1 - 10 of 105,830

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

A recursive statistical translation model

by Juan Miguel Vilar, Enrique Vidal, Dpto De Sistemas Informáticos - ACL 2005 Workshop on Building and Using Parallel Texts: Data-Driven Machine Translation and Beyond, 199–207. Ann Arbor , 2005
"... A new model for statistical translation is presented. A novel feature of this model is that the alignments it produces are hier-archically arranged. The generative pro-cess begins by splitting the input sen-tence in two parts. Each of the parts is translated by a recursive application of the model a ..."
Abstract - Cited by 9 (2 self) - Add to MetaCart
A new model for statistical translation is presented. A novel feature of this model is that the alignments it produces are hier-archically arranged. The generative pro-cess begins by splitting the input sen-tence in two parts. Each of the parts is translated by a recursive application of the model

A Syntax-based Statistical Translation Model

by Kenji Yamada And , 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 estimated ..."
Abstract - 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

Using Statistical Translation Models for Bilingual IR

by Jian-Yun Nie Michel, Michel Simard, Université De Montréal - In CLEF ’01: Revised Papers from the Second Workshop of the Cross-Language Evaluation Forum on Evaluation of Cross-Language Information Retrieval Systems , 2002
"... This report describes our test on using statistical translation models for bilingual IR tasks in CLEF-2001. These translation models have been trained on a set of parallel web pages automatically mined from the Web. Our goal is to compare the following approaches: - using the original parallel co ..."
Abstract - Add to MetaCart
This report describes our test on using statistical translation models for bilingual IR tasks in CLEF-2001. These translation models have been trained on a set of parallel web pages automatically mined from the Web. Our goal is to compare the following approaches: - using the original parallel

Symmetric statistical translation models for automatic image annotation

by Feng Kang, Rong Jin - in The 2005 SIAM Conference on Data Mining (SDM 2005 , 2005
"... Automatic image annotation provides means for users to search image collections on the semantic level using natural language queries. In the past, statistical machine translation models have been successfully applied to automatic image annotation. A problem with this approach is that, due to the ske ..."
Abstract - Cited by 2 (0 self) - Add to MetaCart
Automatic image annotation provides means for users to search image collections on the semantic level using natural language queries. In the past, statistical machine translation models have been successfully applied to automatic image annotation. A problem with this approach is that, due

Symmetric Statistical Translation Models for Automatic Image Annotation

by unknown authors
"... Automatic image annotation provides means for users to search image collections on the semantic level using natural language queries. In the past, statistical machine translation models have been successfully applied to automatic image annotation. A problem with this approach is that, due to the ske ..."
Abstract - Add to MetaCart
Automatic image annotation provides means for users to search image collections on the semantic level using natural language queries. In the past, statistical machine translation models have been successfully applied to automatic image annotation. A problem with this approach is that, due

Statistical phrase-based translation

by Franz Josef Och, Daniel Marcu , 2003
"... We propose a new phrase-based translation model and decoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models. Within our framework, we carry out a large number of experiments to understand better and explain why phrase-based models outpe ..."
Abstract - Cited by 944 (11 self) - Add to MetaCart
We propose a new phrase-based translation model and decoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models. Within our framework, we carry out a large number of experiments to understand better and explain why phrase-based models

Cognates Can Improve Statistical Translation Models

by Grzegorz Kondrak, Daniel Marcu, Keven Knight - In Proceedings of HLT-NAACL 2003 (companion volume , 2003
"... We report results of experiments aimed at improving the translation quality by incorporating the cognate information into translation models. ..."
Abstract - Cited by 28 (2 self) - Add to MetaCart
We report results of experiments aimed at improving the translation quality by incorporating the cognate information into translation models.

Hope and Fear for Discriminative Training of Statistical Translation Models

by David Chiang, Michael Collins
"... In machine translation, discriminative models have almost entirely supplanted the classical noisychannel model, but are standardly trained using a method that is reliable only in low-dimensional spaces. Two strands of research have tried to adapt more scalable discriminative training methods to mach ..."
Abstract - Cited by 8 (0 self) - Add to MetaCart
In machine translation, discriminative models have almost entirely supplanted the classical noisychannel model, but are standardly trained using a method that is reliable only in low-dimensional spaces. Two strands of research have tried to adapt more scalable discriminative training methods

Moses: Open Source Toolkit for Statistical Machine Translation

by Philipp Koehn, Hieu Hoang, Alexandra Birch, Chris Callison-burch, Richard Zens, Marcello Federico, Nicola Bertoldi, Chris Dyer, Brooke Cowan, Wade Shen, Christine Moran, Ondrej Bojar, Alexandra Constantin, Evan Herbst - ACL , 2007
"... We describe an open-source toolkit for statistical machine translation whose novel contributions are (a) support for linguistically motivated factors, (b) confusion network decoding, and (c) efficient data formats for translation models and language models. In addition to the SMT decoder, the toolki ..."
Abstract - Cited by 1517 (66 self) - Add to MetaCart
We describe an open-source toolkit for statistical machine translation whose novel contributions are (a) support for linguistically motivated factors, (b) confusion network decoding, and (c) efficient data formats for translation models and language models. In addition to the SMT decoder
Results 1 - 10 of 105,830