Sciweavers

460 search results - page 60 / 92
» Evaluation in the context of natural language generation
Sort
View
CICLING
2009
Springer
14 years 9 months ago
Enriching Statistical Translation Models Using a Domain-Independent Multilingual Lexical Knowledge Base
This paper presents a method for improving phrase-based Statistical Machine Translation systems by enriching the original translation model with information derived from a multilin...
Miguel García, Jesús Giménez,...
ESWS
2008
Springer
13 years 10 months ago
Enriching an Ontology with Multilingual Information
Organizations working in a multilingual environment demand multilingual ontologies. To solve this problem we propose LabelTranslator, a system that automatically localizes ontologi...
Mauricio Espinoza, Asunción Gómez-P&...
CICLING
2006
Springer
14 years 6 days ago
Automatic Acquisition of Semantic-Based Question Reformulations for Question Answering
Abstract. In this paper, we present a method for the automatic acquisition of semantic-based reformulations from natural language questions. Our goal is to find useful and generic ...
Jamileh Yousefi, Leila Kosseim
CICLING
2009
Springer
14 years 9 months ago
Guessers for Finite-State Transducer Lexicons
Abstract. Language software applications encounter new words, e.g., acronyms, technical terminology, names or compounds of such words. In order to add new words to a lexicon, we ne...
Krister Lindén
ACL
2006
13 years 10 months ago
Minimum Risk Annealing for Training Log-Linear Models
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
David A. Smith, Jason Eisner