Skip to main content

TRADUCCION AUTOMATICA NEURONAL, EN DOMINIO, NO SUPERVISADA

PGC2018-102041-B-I00

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal de Generación de Conocimiento y Fortalecimiento Científico y Tecnológico del Sistema de I+D+i
Subprogram Subprograma Estatal de Generación de Conocimiento
Call Proyectos de I+D (Excelencia / Generación de Conocimiento)
Call year 2018
State Plan 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSIDAD DEL PAIS VASCO EUSKAL HERRIKO UNIBERTSITATEA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

RUA. Repositorio Institucional de la Universidad de Alicante
Publication Otros (Other)

Can translationese features help users select an MT system for post-editing?, ¿Pueden ayudar las características del traduccionés a los usuarios a seleccionar un sistema de TA para posedición?

  • Aranberri, Nora
This work explores the possibility of using translationese features as indicators of machine translation quality for users to select an MT system for post-editing assuming that a lower level of translationese will reveal a reduced need for editing. Results reveal that translationese and automatic metrics rank systems differently, opening an avenue for further research into the information each provides.
RUA. Repositorio Institucional de la Universidad de Alicante
Publication Otros (Other)

Cross-lingual Diachronic Distance: Application to Portuguese and Spanish, Distancia diacrónica interlingüística: aplicación al portugués y el castellano

  • Pichel Campos, José Ramom
  • Gamallo Otero, Pablo
  • Alegría Loinaz, Iñaki
The aim of this paper is to establish a corpus-based methodology for automatically measuring the cross-lingual distance between historical periods of two languages using perplexity. The corpus of both has been constructed adhoc with the closest spelling to the original representing chronologically and in a balanced way fiction and non-fiction. The methodology has been applied to two related languages, Portuguese and Spanish, and measured their diachronic distances both in original orthography and in an automatically transcribed spelling.
RUA. Repositorio Institucional de la Universidad de Alicante
Publication Otros (Other)

Using Dependency-Based Contextualization for transferring Passive Constructions from English to Spanish, Contextualización basada en dependencias sintácticas para transferir construcciones pasivas de inglés a español

  • Gamallo Otero, Pablo
  • Labaka Intxauspe, Gorka
We hypothesize that parallel corpora as well as machine translation outputs contain many literal translations that are the result of transferring the constructions of the source language to the target language. When translating passive expressions from English to Spanish, there are several constructions available, however, both automatic and human (if of low quality) translations tend to select the periphrastic structure, which is the literal construction. The objective of this article is to make use of strategies trained on monolingual corpora to translate English passive expressions into Spanish so as to verify whether unsupervised translation with monolingual corpora benefits syntactic diversity. Special attention will be given to the monolingual-based strategy relying on dependency-based contextualization. The results of the experiments carried out show that the methods relying on monolingual corpora tend to offer more non-literal translations (middle-voice) than those trained on parallel corpora.