Automatic Correction of Human Translations

06/17/2022
by   Jessy Lin, et al.
8

We introduce translation error correction (TEC), the task of automatically correcting human-generated translations. Imperfections in machine translations (MT) have long motivated systems for improving translations post-hoc with automatic post-editing. In contrast, little attention has been devoted to the problem of automatically correcting human translations, despite the intuition that humans make distinct errors that machines would be well-suited to assist with, from typos to inconsistencies in translation conventions. To investigate this, we build and release the Aced corpus with three TEC datasets. We show that human errors in TEC exhibit a more diverse range of errors and far fewer translation fluency errors than the MT errors in automatic post-editing datasets, suggesting the need for dedicated TEC models that are specialized to correct human errors. We show that pre-training instead on synthetic errors based on human errors improves TEC F-score by as much as 5.1 points. We conducted a human-in-the-loop user study with nine professional translation editors and found that the assistance of our TEC system led them to produce significantly higher quality revised translations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/01/2019

Post-editese: an Exacerbated Translationese

Post-editing (PE) machine translation (MT) is widely used for disseminat...
research
03/20/2018

eSCAPE: a Large-scale Synthetic Corpus for Automatic Post-Editing

Training models for the automatic correction of machine-translated text ...
research
09/15/2017

Transcribing Against Time

We investigate the problem of manually correcting errors from an automat...
research
04/29/2020

Learning Non-Monotonic Automatic Post-Editing of Translations from Human Orderings

Recent research in neural machine translation has explored flexible gene...
research
03/15/2022

Can Synthetic Translations Improve Bitext Quality?

Synthetic translations have been used for a wide range of NLP tasks prim...
research
09/26/2018

Wronging a Right: Generating Better Errors to Improve Grammatical Error Detection

Grammatical error correction, like other machine learning tasks, greatly...
research
08/12/2023

With a Little Help from the Authors: Reproducing Human Evaluation of an MT Error Detector

This work presents our efforts to reproduce the results of the human eva...

Please sign up or login with your details

Forgot password? Click here to reset