Applying MTPE to Sworn Translation: Bonus or Burden?

This article reports on a study that aimed to investigate the productivity of machine translation post-editing (MTPE) applied to the sworn translation of personal documents. More specifically, it aimed at describing some of the challenges of post-editing birth certificates and ID cards from Brazilian Portuguese into American English, as well as analyzing the time spent on the MTPE of such documents in comparison to manually translating them. The methodology consisted of timed and annotated translation using MTPE and human translation (HT). It also included the description of elements and final formatting that is characteristic of sworn translation. The PDF files were converted to Word using an OCR software. Our results indicated that MTPE might be more productive than HT when time spent on OCR and formatting is not considered. However, since the sample size was limited to eight documents and two types of documents, the results cannot be generalized.

Authors

Institutions

Publication Details

Journal
Belas Infiéis
Published
2024-11-12
DOI
https://doi.org/10.26512/belasinfieis.v13.n1.2024.54644
Primary Topic
Text Readability and Simplification
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Applying MTPE to Sworn Translation: Bonus or Burden?

Arlene Koglin, Aíla Fonseca de Albuquerque
Belas Infiéis
Text Readability and Simplification
article

Applying MTPE to Sworn Translation: Bonus or Burden?

Arlene Koglin, Aíla Fonseca de Albuquerque
article en

Abstract

This article reports on a study that aimed to investigate the productivity of machine translation post-editing (MTPE) applied to the sworn translation of personal documents. More specifically, it aimed at describing some of the challenges of post-editing birth certificates and ID cards from Brazilian Portuguese into American English, as well as analyzing the time spent on the MTPE of such documents in comparison to manually translating them. The methodology consisted of timed and annotated translation using MTPE and human translation (HT). It also included the description of elements and final formatting that is characteristic of sworn translation. The PDF files were converted to Word using an OCR software. Our results indicated that MTPE might be more productive than HT when time spent on OCR and formatting is not considered. However, since the sample size was limited to eight documents and two types of documents, the results cannot be generalized.

Belas InfiéisVol. 13(1)
Universidade Federal de Pernambuco (BR)
Openalex Percentile: Top 76%
Text Readability and Simplification
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.