Please use this identifier to cite or link to this item:

http://hdl.handle.net/10609/108607
Title: La aplicación de sistemas de traducción automática estadística y neuronal para la traducción del inglés al español de artículos especializados en el campo de las ciencias de la ingeniería
Author: Tejeda Achondo, Ignacio Daniel
Tutor: Mesa Lao, Bartolomé
Keywords: terminology
statistical machine translation
neural machine translation
specialized texts
translation assessment
translation errors
Issue Date: 20-Jan-2020
Publisher: Universitat Oberta de Catalunya (UOC)
Abstract: This paper presents an analysis and comparison of the performance of two freeware machine translation systems with hybrid techniques (statistics and neural), in the translation from English to Spanish of abstracts in research papers of Hydraulic Engineering and modeling of groundwater flow. Eight articles were selected on the indicated subject from international journals of Engineering Science. Google Translate and Bing Microsoft Translator were used to translate the abstracts. Three analyzes were performed: 1) a review of the total word count after the translations were completed; 2) a quality assessment of the translations of the sentences using a scale from 1 (perfectly clear sentences) to 4 (totally incomprehensible sentences); and 3) an analysis of the errors, following a methodology of classification by typologies, such as precision errors (terminology, word choice, omissions, etc.) and fluency (grammar, spelling, etc.). It is shown that both systems produced acceptable translations but still require manual work to achieve professional results, and Google Translate is a better machine translator for this type of specialized texts.
Language: Spanish
URI: http://hdl.handle.net/10609/108607
Appears in Collections:Bachelor thesis, research projects, etc.

Share:
Export:
Files in This Item:
File Description SizeFormat 
idtaTFM0120memoria.pdfMemoria del TFM852.33 kBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons