A review of the state-of-the-art in automatic post-editing

Carmo, Félix do; Shterionov, Dimitar; Moorkens, Joss; Wagner, Joachim; Hossari, Murhaf; Paquin, Eric; Schmidtke, Dag; Groves, Declan; Way, Andy

doi:10.1007/s10590-020-09252-y

Cited by 19 publications

(15 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Just like MT systems, APE was first based on rules and then adopted statistical methods before utilising machine learning and neural networks. Since 2006, when Llitjós and Carbonell [4] raised the issue of a lack of fully automatic solutions to PE, APE has regained popularity with the first APE shared task at the WMT conference series [5]. These have been running regularly ever since, providing datasets and a forum for discussing the latest advances in this field.…”

Section: Automatic Post-editingmentioning

confidence: 99%

“…However, significant improvements were later achieved, when APE systems began to use neural approaches [7]. Despite this, it is common for APE systems to produce overcorrections and to fail to detect certain errors [5]. Moreover, APE became even more challenging, as Neural MT (NMT) provides translations of a higher quality compared to previous MT systems, thus making automatic correction a more complex task [5,8].…”

Section: Automatic Post-editingmentioning

confidence: 99%

“…Despite this, it is common for APE systems to produce overcorrections and to fail to detect certain errors [5]. Moreover, APE became even more challenging, as Neural MT (NMT) provides translations of a higher quality compared to previous MT systems, thus making automatic correction a more complex task [5,8]. In fact, the usefulness of APE models resides in the improvement margin observed in MT outputs [5].…”

Section: Automatic Post-editingmentioning

confidence: 99%

See 2 more Smart Citations

Interactive Models for Post-Editing

Escribe¹,

Mitkov²

2021

Proceedings of the Translation and Interpreting Technology Online Conference TRITON 2021

View full text Add to dashboard Cite

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-progress paper discusses APE models and suggests that they could be improved in more interactive scenarios, as previously done in MT with the creation of Interactive MT (IMT) systems. Based on the hypothesis that PE would benefit from HCI, two methodologies are proposed. Both suggest that traditional batch learning settings are not optimal for PE. Instead, online techniques are recommended to train and update PE models on the fly, via either real or simulated interactions with the translator.

show abstract

Section: Automatic Post-editingmentioning

confidence: 99%

Section: Automatic Post-editingmentioning

confidence: 99%

Section: Automatic Post-editingmentioning

confidence: 99%

See 1 more Smart Citation

Interactive Models for Post-Editing

Escribe¹,

Mitkov²

2021

Proceedings of the Translation and Interpreting Technology Online Conference TRITON 2021

View full text Add to dashboard Cite

show abstract

“…This allows the user to select or rank the system that exhibits the best translation results [2]. In addition, for low-quality sentences, efficiency can be increased during automatic post editing [3] by modifying only the low-quality words or phrases using quality annotations. Therefore, QE is an important process that can be widely applied.…”

Section: Introductionmentioning

confidence: 99%

Comparative Analysis of Current Approaches to Quality Estimation for Neural Machine Translation

Park

Moon

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

Quality estimation (QE) has recently gained increasing interest as it can predict the quality of machine translation results without a reference translation. QE is an annual shared task at the Conference on Machine Translation (WMT), and most recent studies have applied the multilingual pretrained language model (mPLM) to address this task. Recent studies have focused on the performance improvement of this task using data augmentation with finetuning based on a large-scale mPLM. In this study, we eliminate the effects of data augmentation and conduct a pure performance comparison between various mPLMs. Separate from the recent performance-driven QE research involved in competitions addressing a shared task, we utilize the comparison for sub-tasks from WMT20 and identify an optimal mPLM. Moreover, we demonstrate QE using the multilingual BART model, which has not yet been utilized, and conduct comparative experiments and analyses with cross-lingual language models (XLMs), multilingual BERT, and XLM-RoBERTa.

show abstract

“…Finally, multiple recently published studies [18,19] confirm that PE continues to be a vibrant research topic at the intersection of translation process research, natural language processing, and human-computer interaction. Current relevant research directions include multi-modal PE [20,21], in which PE systems take several forms of input such as speech, touch, and gaze in addition to the usual keystrokes, and automatic post-editing (APE) [22][23][24], which attempts to automatise corrections commonly carried out in the MT output by human translators during the PE process.…”

Section: Introductionmentioning

confidence: 99%

The Role of Machine Translation Quality Estimation in the Post-Editing Workflow

Béchara

Orăsan

Escartín³

et al. 2021

Informatics

View full text Add to dashboard Cite

As Machine Translation (MT) becomes increasingly ubiquitous, so does its use in professional translation workflows. However, its proliferation in the translation industry has brought about new challenges in the field of Post-Editing (PE). We are now faced with a need to find effective tools to assess the quality of MT systems to avoid underpayments and mistrust by professional translators. In this scenario, one promising field of study is MT Quality Estimation (MTQE), as this aims to determine the quality of an automatic translation and, indirectly, its degree of post-editing difficulty. However, its impact on the translation workflows and the translators’ cognitive load is still to be fully explored. We report on the results of an impact study engaging professional translators in PE tasks using MTQE. To assess the translators’ cognitive load we measure their productivity both in terms of time and effort (keystrokes) in three different scenarios: translating from scratch, post-editing without using MTQE, and post-editing using MTQE. Our results show that good MTQE information can improve post-editing efficiency and decrease the cognitive load on translators. This is especially true for cases with low MT quality.

show abstract

A review of the state-of-the-art in automatic post-editing

Cited by 19 publications

References 59 publications

Interactive Models for Post-Editing

Interactive Models for Post-Editing

Comparative Analysis of Current Approaches to Quality Estimation for Neural Machine Translation

The Role of Machine Translation Quality Estimation in the Post-Editing Workflow

Contact Info

Product

Resources

About