Bound Volume Number
Volume V
Degree Type
Honors Capstone Project
Date of Submission
Spring 5-2016
Capstone Advisor
Maria Emma Ticio Quesada
Capstone Major
Languages, Literatures, and Linguistics
Capstone College
Arts and Science
Audio/Visual Component
no
Keywords
the differences between human and machine translation
Capstone Prize Winner
no
Won Capstone Funding
no
Honors Categories
Humanities
Subject Categories
Spanish and Portuguese Language and Literature
Abstract
Machine translation systems experience a trade-off between efficiency and efficacy: while quicker and easier than human translation, machine translations are less accurate and comprehensible.
This study analyzes two sets of English to Spanish translations to compare the differences between human and machine translation and evaluate the performance of machine translation. Google Translate—the best-performing machine translator—represents machine translation as a whole in producing English to Spanish translations of the given text. The primary investigator—a non-native speaker and graduating student of Spanish Language, Literature & Culture at Syracuse University—serves as the benchmark for the average non-native speaker of Spanish at the advanced-mid level of proficiency. Findings are divided into four groups: lexical findings, sentential findings, phrasal findings, and stylistic findings.
From these findings, the study is able to establish that machine translation struggles to decipher context, which results in errors in word choice and lack of proper technical language; displays inconsistency in its errors, and lacks the capability to learn. Such individual findings led to the overall conclusion that Google Translate—and thus machine translation—performs below the level of an average non-native speaker of Spanish.
Recommended Citation
Howell, Nicole, "Applying Linguistics: Analyzing the Differences Between Human and Machine Translation of Selected Texts" (2016). Renée Crown University Honors Thesis Projects - All. 940.
https://surface.syr.edu/honors_capstone/940
Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.