منابع مشابه
Sistema Estadístico de Reordenamiento de Palabras en Traducción Automática
Nowadays, reordering is one of the most important problems in Statistical Machine Translation (SMT) systems. This paper exposes a novel strategy to face it: Statistical Machine Reordering (SMR). It consists of using the powerful techniques developed for Statistical Machine Translation (SMT) in order to translate the source language (S) into a reordered source language (S’), which allows for an ...
متن کاملLocalización de Palabras basada en Grafos de Fonemas
In this paper we propose the use of phoneme graphs for word spotting tasks. The proposed phoneme graphs are built using phonetic probabilities estimated at frame level. We also propose an error model on phoneme graphs which allows to simplify the exploration algorithms used for finding phonetic sequences. A phoneme duration model is also applied for avoiding the detection of too short phonetic ...
متن کاملDetectando la prioridad de contenidos generados en Twitter por medio de n-gramas de palabras
Resumen. En la actualidad, el uso de las redes sociales ha revolucionado la forma en que los usuarios intercambian ideas, opiniones e información. Gracias a este cambio de paradigma en la forma de interactuar entre los usuarios, las grandes compañ́ıas y personajes públicos han comenzado a prestar particular interés a la opinión generada respecto a sus productos y/o servicios, actos y/o eventos d...
متن کاملReglas de formación de palabras compuestas en español para la automatización de su reconocimiento
The following work presents the formation rules and application criteria that should be carried out in each situation in order to obtain the automated identification of one of the word’s formation processes in Spanish. In the composition are studied only those cases in which this phenomenon has been produced through the graphic link of the elements involved, aimed to automation. At this aim, di...
متن کاملRedes de palabras alineadas como recurso en la extracción de equivalencias léxicas de traducción y su aplicación en la alineación
The notion of lexical translation equivalent is defined via correspondence established between two languages conventionally called source and target languages. We propose a method for extraction such equivalents for non-functional words. Our algorithm is based in two main resources: (1) MultiWordNet as a specialized lexicon for each one of the two languages in question and (2) a parallel text c...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Estudios: filosofía, historia, letras
سال: 2012
ISSN: 0185-6383
DOI: 10.5347/01856383.0100.000188494