Proceedings of the Translation and Interpreting Technology Online Conference TRITON 2021 2021
DOI: 10.26615/978-954-452-071-7_019
|View full text |Cite
|
Sign up to set email alerts
|

Interactive Models for Post-Editing

Abstract: Despite the increasingly good quality of Machine Translation (MT) systems, MT outputs require corrections. Automatic Post-Editing (APE) models have been introduced to perform these corrections without human intervention. However, no system has been able to fully automate the Post-Editing (PE) process. Moreover, while numerous translation tools, such as Translation Memories (TMs), largely benefit from translators' input, Human-Computer Interaction (HCI) remains limited when it comes to PE. This research-in-prog… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1
1

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 14 publications
(18 reference statements)
0
2
0
Order By: Relevance
“…Instead of fully automating the post-editing task, Escribe and Mitkov (2021) suggest that postediting would greatly benefit from human-centered approaches that leverage the post-editor's corrections and their interactions with the translation interface. For example, APE models could improve over time by incrementally learning from human corrections (Chatterjee et al, 2017).…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…Instead of fully automating the post-editing task, Escribe and Mitkov (2021) suggest that postediting would greatly benefit from human-centered approaches that leverage the post-editor's corrections and their interactions with the translation interface. For example, APE models could improve over time by incrementally learning from human corrections (Chatterjee et al, 2017).…”
Section: Introductionmentioning
confidence: 99%
“…While human-computer interaction has been explored in MT with the help of translation frameworks such as CASMACAT (Alabau et al, 2013), there is no such interactive environment designed for the post-editing task (do Carmo et al, 2020;Escribe and Mitkov, 2021). Therefore, current research in Interactive Post-Editing (IPE) is limited to simulate the human interaction by feeding pre-existing corrections to the post-editing process sequentially (Ortiz-Martínez and Casacuberta, 2014;Chatterjee et al, 2017;Negri et al, 2018a).…”
Section: Introductionmentioning
confidence: 99%