Separating translation correction post-edits from content improvement post-edits in machine translated content

Machine learning models can determine whether post-edits to machine translated content are corrective post-edits, which are edits made to correct translation errors caused during machine translation, or content improvement post-edits, which are post-edits that have been made to improve source langua...

Full description

Saved in:
Bibliographic Details
Main Authors Hieber, Felix, Fuerstenau, Hagen
Format Patent
LanguageEnglish
Published 02.04.2019
Subjects
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Machine learning models can determine whether post-edits to machine translated content are corrective post-edits, which are edits made to correct translation errors caused during machine translation, or content improvement post-edits, which are post-edits that have been made to improve source language content. The corrective post-edits can be utilized to generate or modify labels for strings utilized to train a translation quality estimation system. The content improvement post-edits can be utilized to improve the quality of source content prior to providing the source content to the machine translation system for translation.
Bibliography:Application Number: US201615360286