Can Automatic Post-Editing Improve NMT?
Automatic post-editing (APE) aims to improve machine translations, thereby reducing human post-editing effort. APE has had notable success when used with statistical machine translation (SMT) systems but has not been as successful over neural machine translation (NMT) systems. This has raised questions on the relevance of APE task in the current scenario. However, the training of APE models has been heavily reliant on large-scale artificial corpora combined with only limited human post-edited data. We hypothesize that APE models have been underperforming in improving NMT translations due to the lack of adequate supervision. To ascertain our hypothesis, we compile a larger corpus of human post-edits of English to German NMT. We empirically show that a state-of-art neural APE model trained on this corpus can significantly improve a strong in-domain NMT system, challenging the current understanding in the field. We further investigate the effects of varying training data sizes, using artificial training data, and domain specificity for the APE task. We release this new corpus under CC BY-NC-SA 4.0 license at https://github.com/shamilcm/pedra.
Code (1)
Tasks
Automatic Post-EditingMachine TranslationNMTSpecificityTranslationSimilar Papers 제목 키워드 기반
PET: a Tool for Post-editing and Assessing Machine Translation
Given the significant improvements in Machine Translation (MT) quality and the increasing demand for translations, post-editing of automatic translations is becoming a popular practice in the translation industry. It has…
Machine TranslationSentenceTranslationAdapting Neural Machine Translation for Automatic Post-Editing
Automatic post-editing (APE) models are usedto correct machine translation (MT) system outputs by learning from human post-editing patterns. We present the system used in our submission to the WMT’21 Automatic Post-Editi…
Automatic Post-EditingMachine TranslationTranslationLeveraging GPT-4 for Automatic Translation Post-Editing
While Neural Machine Translation (NMT) represents the leading approach to Machine Translation (MT), the outputs of NMT models still require translation post-editing to rectify errors and enhance quality under critical se…
Machine TranslationNMTTranslationMulti-encoder Transformer Network for Automatic Post-Editing
This paper describes the POSTECH{'}s submission to the WMT 2018 shared task on Automatic Post-Editing (APE). We propose a new neural end-to-end post-editing model based on the transformer network. We modified the encoder…
Automatic Post-EditingDecoderMachine TranslationNMT+1LIG-CRIStAL System for the WMT17 Automatic Post-Editing Task
This paper presents the LIG-CRIStAL submission to the shared Automatic Post- Editing task of WMT 2017. We propose two neural post-editing models: a monosource model with a task-specific attention mechanism, which perform…
Automatic Post-Editingde-enSentence