This paper describes Netmarble's submission to WMT21 Automatic Post-Editing (APE) Shared Task for the English-German language pair. First, we propose a Curriculum Training Strategy in training stages. Facebook Fair's WMT19 news translation model was
chosen to engage the large and powerful pre-trained neural networks. Then, we post-train the translation model with different levels of data at each training stages. As the training stages go on, we make the system learn to solve multiple tasks by adding extra information at different training stages gradually. We also show a way to utilize the additional data in large volume for APE tasks. For further improvement, we apply Multi-Task Learning Strategy with the Dynamic Weight Average during the fine-tuning stage. To fine-tune the APE corpus with limited data, we add some related subtasks to learn a unified representation. Finally, for better performance, we leverage external translations as augmented machine translation (MT) during the post-training and fine-tuning. As experimental results show, our APE system significantly improves the translations of provided MT results by -2.848 and +3.74 on the development dataset in terms of TER and BLEU, respectively. It also demonstrates its effectiveness on the test dataset with higher quality than the development dataset.
This paper introduces data on translation trainees' perceptions of the MTPE process and implications on training in this field. This study aims to analyse trainees' performance of three MTPE tasks the English-Polish language pair and post-tasks inter
views to determine the need to promote machine translation post-editing skills in educating translation students. Since very little information concerning MTPE training is available, this study may be found advantageous.
Production NMT systems typically need to serve niche domains that are not covered by adequately large and readily available parallel corpora. As a result, practitioners often fine-tune general purpose models to each of the domains their organisation
caters to. The number of domains however can often become large, which in combination with the number of languages that need serving can lead to an unscalable fleet of models to be developed and maintained. We propose Multi Dimensional Tagging, a method for fine-tuning a single NMT model on several domains simultaneously, thus drastically reducing development and maintenance costs. We run experiments where a single MDT model compares favourably to a set of SOTA specialist models, even when evaluated on the domain those baselines have been fine-tuned on. Besides BLEU, we report human evaluation results. MDT models are now live at Booking.com, powering an MT engine that serves millions of translations a day in over 40 different languages.
Language technology is already largely adopted by most Language Service Providers (LSPs) and integrated into their traditional translation processes. In this context, there are many different approaches to applying Post-Editing (PE) of a machine tran
slated text, involving different workflow processes and steps that can be more or less effective and favorable. In the present paper, we propose a 3-step Post-Editing Workflow (PEW). Drawing from industry insight, this paper aims to provide a basic framework for LSPs and Post-Editors on how to streamline Post-Editing workflows in order to improve quality, achieve higher profitability and better return on investment and standardize and facilitate internal processes in terms of management and linguist effort when it comes to PE services. We argue that a comprehensive PEW consists in three essential tasks: Pre-Editing, Post-Editing and Annotation/Machine Translation (MT) evaluation processes (Guerrero, 2018) supported by three essential roles: Pre-Editor, Post-Editor and Annotator (Gene, 2020). Furthermore, the pre-sent paper demonstrates the training challenges arising from this PEW, supported by empirical research results, as reflected in a digital survey among language industry professionals (Gene, 2020), which was conducted in the context of a Post-Editing Webinar. Its sample comprised 51 representatives of LSPs and 12 representatives of SLVs (Single Language Vendors) representatives.
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 a
ble 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.
This paper provides a quick overview of possible methods how to detect that reference translations were actually created by post-editing an MT system. Two methods based on automatic metrics are presented: BLEU difference between the suspected MT and
some other good MT and BLEU difference using additional references. These two methods revealed a suspicion that the WMT 2020 Czech reference is based on MT. The suspicion was confirmed in a manual analysis by finding concrete proofs of the post-editing procedure in particular sentences. Finally, a typology of post-editing changes is presented where typical errors or changes made by the post-editor or errors adopted from the MT are classified.
