Automatic Post-Editing of Machine Translation: A Neural Programmer-Interpreter Approach

Vu, Thuy-Trang; Haffari, Gholamreza

doi:10.18653/v1/d18-1341

Cited by 20 publications

(16 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Post-editing is also determined as the modification process of the machine translation output with a minimum labour effort rather than re-translation of the text. Automatic post-editing aims to correct the systematic and repetitive errors found in the output of machine translation [4]. In this concern, in another research, online automatic postediting system is introduced as trained on generic data and its exploiting user feedback to develop its performance.…”

Section: Literature Review and Discussionmentioning

confidence: 99%

The Opportunities and the Limitations of Using the Independent Post-Editor Technology in Translation Education

Türkmen¹,

Zahit²

2019

ijacsa

View full text Add to dashboard Cite

A new mechanical function known as post-editing, which helps to correct the imperfections of raw machine translation output, is introduced in the translation market. While this function is commonly used as an integral part of the machine translation, it can also be used for correcting non-translated texts on its own. The main purpose of this study is to find an answer to the question of which contributions could be made to the competences of translation students by using independent posteditors during academic translation education. A model course application and survey are conducted with the participation of students from translation studies departments. The interrater reliability is used in this study. In accordance with the results, it is found that most of the students have not known the usage of the independent post-editors during the translation process. The research provides new insights into the contributions of posteditor technology to the translation education. The findings of the research also reflect the contributions of post-editor technology to the translation quality in terms of the speed-time management, the accuracy of punctuations, abbreviations, and grammar rules. It is also determined that the post-editors contribute to the competencies of the translation students. As a result, it is suggested that the post-editors may be used as an educational material in translation education. Indeed, the results require other studies about the usage of post-editors as educational materials.

show abstract

Section: Literature Review and Discussionmentioning

confidence: 99%

The Opportunities and the Limitations of Using the Independent Post-Editor Technology in Translation Education

Türkmen¹,

Zahit²

2019

ijacsa

View full text Add to dashboard Cite

show abstract

“…NPI is adopted in text editing to predict tags, such as KEEP, DELETE, and INSERT, and execute operations during decoding simultaneously. NPI-based methods have achieved state-of-the-art results in long-to-short (Dong et al, 2019;Gu et al, 2019), and mixed editing (Vu and Haffari, 2018). Nevertheless, like other Tagging methods, NPI's encoder hidden states are not updated during editing.…”

Section: Related Workmentioning

confidence: 99%

Recurrent Inference in Text Editing

Shi

Zeng

Zhang³

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

In neural text editing, prevalent sequence-tosequence based approaches directly map the unedited text either to the edited text or the editing operations, in which the performance is degraded by the limited source text encoding and long, varying decoding steps. To address this problem, we propose a new inference method, Recurrence, that iteratively performs editing actions, significantly narrowing the problem space. In each iteration, encoding the partially edited text, Recurrence decodes the latent representation, generates an action of short, fixed-length, and applies the action to complete a single edit. For a comprehensive comparison, we introduce three types of text editing tasks: Arithmetic Operators Restoration (AOR), Arithmetic Equation Simplification (AES), Arithmetic Equation Correction (AEC). Extensive experiments on these tasks with varying difficulties demonstrate that Recurrence achieves improvements over conventional inference methods.

show abstract

“…COPYNET (Gu et al, 2016;Zhao et al, 2019): the multi-source Transformer equipped with CopyNet (see Figure 2(a)). (Vu and Haffari, 2018): a neural programmer-interpreter approach. We implemented COPYNET also on top of THUMT (Zhang et al, 2017).…”

Section: Baselinesmentioning

confidence: 99%

Learning to Copy for Automatic Post-Editing

Huang

Liu

Luan

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Automatic post-editing (APE), which aims to correct errors in the output of machine translation systems in a post-processing step, is an important task in natural language processing. While recent work has achieved considerable performance gains by using neural networks, how to model the copying mechanism for APE remains a challenge. In this work, we propose a new method for modeling copying for APE. To better identify translation errors, our method learns the representations of source sentences and system outputs in an interactive way. These representations are used to explicitly indicate which words in the system outputs should be copied, which is useful to help CopyNet (Gu et al., 2016) better generate post-edited translations. Experiments on the datasets of the WMT 2016-2017 APE shared tasks show that our approach outperforms all best published results.

show abstract

Automatic Post-Editing of Machine Translation: A Neural Programmer-Interpreter Approach

Cited by 20 publications

References 9 publications

The Opportunities and the Limitations of Using the Independent Post-Editor Technology in Translation Education

The Opportunities and the Limitations of Using the Independent Post-Editor Technology in Translation Education

Recurrent Inference in Text Editing

Learning to Copy for Automatic Post-Editing

Contact Info

Product

Resources

About