Why Predicting Post-Edition is so Hard? Failure Analysis of LIMSI Submission to the APE Shared Task

Wisniewski, Guillaume; Pécheux, Nicolas; Yvon, François

doi:10.18653/v1/w15-3027

Cited by 5 publications

(6 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The higher is the value of the negimpact feature, the less useful is the translation option. After pruning, the final stage of the APE pipeline tries to raise the capability of the decoder to select the correct translation rule by the introduction of new task specific features integrated in (Wisniewski et al, 2015) USAAR-SAPE Saarland University, Germany & Jadavpur University, India (Pal et al, 2015b) the model. These features measure the similarity and the reliability of the translation options and help to improve the precision of the resulting APE system.…”

Section: Participantsmentioning

confidence: 99%

See 1 more Smart Citation

Findings of the 2015 Workshop on Statistical Machine Translation

Bojar

Chatterjee

Federmann

et al. 2015

Proceedings of the Tenth Workshop on Statistical Machine Translation

218

222

View full text Add to dashboard Cite

This paper presents the results of the WMT14 shared tasks, which included a standard news translation task, a separate medical translation task, a task for run-time estimation of machine translation quality, and a metrics task. This year, 143 machine translation systems from 23 institutions were submitted to the ten translation directions in the standard translation task. An additional 6 anonymized systems were included, and were then evaluated both automatically and manually. The quality estimation task had four subtasks, with a total of 10 teams, submitting 57 entries.

show abstract

Section: Participantsmentioning

confidence: 99%

“…For the first edition of the APE shared task LIMSI submitted two systems (Wisniewski et al, 2015). The first one is based on the approach of Simard et al (2007) and considers the APE task as a monolingual translation between a translation hypothesis and its post-edition.…”

Section: Limsimentioning

confidence: 99%

Findings of the 2015 Workshop on Statistical Machine Translation

Bojar

Chatterjee

Federmann

et al. 2015

Proceedings of the Tenth Workshop on Statistical Machine Translation

218

222

View full text Add to dashboard Cite

show abstract

“…The team from FBK (Chatterjee et al 2015a) addressed data sparsity (most of the entries in the MT phrase table are unique) with a feature that measured the usefulness of each translated unit and pruned away the least useful ones. The team from LIMSI (Wisniewski et al 2015) tried to develop sieves of rules that tackled known grammatical issues. Finally, Pal et al (2015) tested different phrase lengths for the language and the translation model.…”

Section: Wmt 2015: the Stone Age Of Apementioning

confidence: 99%

“…We may go back to the pilot APE shared task in 2015 to see a detailed analysis of data issues beyond the repetitiveness of the training data. Wisniewski et al (2015) presented a system that tried to learn edits by using edit distances. Besides the overcorrection effect mentioned earlier, the authors mention "uniqueness of edits" as a major issue: even the most frequent edits (e.g.…”

Section: Data Issuesmentioning

confidence: 99%

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

Carmo

Shterionov

Moorkens

et al. 2020

Machine Translation

View full text Add to dashboard Cite

This article presents a review of the evolution of automatic post-editing, a term that describes methods to improve the output of machine translation systems, based on knowledge extracted from datasets that include post-edited content. The article describes the specificity of automatic post-editing in comparison with other tasks in machine translation, and it discusses how it may function as a complement to them. Particular detail is given in the article to the five-year period that covers the shared tasks presented in WMT conferences (2015–2019). In this period, discussion of automatic post-editing evolved from the definition of its main parameters to an announced demise, associated with the difficulties in improving output obtained by neural methods, which was then followed by renewed interest. The article debates the role and relevance of automatic post-editing, both as an academic endeavour and as a useful application in commercial workflows.

show abstract

“…Other popular approaches rely on rule-based components (Wisniewski et al, 2015;Béchara et al, 2012) which we do not discuss here.…”

Section: Post-editingmentioning

confidence: 99%

Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing

Junczys-Dowmunt¹,

Grundkiewicz²

2016

Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers

View full text Add to dashboard Cite

This paper describes the submission of the AMU (Adam Mickiewicz University) team to the Automatic Post-Editing (APE) task of WMT 2016. We explore the application of neural translation models to the APE problem and achieve good results by treating different models as components in a log-linear model, allowing for multiple inputs (the MT-output and the source) that are decoded to the same target language (post-edited translations). A simple string-matching penalty integrated within the log-linear model is used to control for higher faithfulness with regard to the raw machine translation output. To overcome the problem of too little training data, we generate large amounts of artificial data. Our submission improves over the uncorrected baseline on the unseen test set by -3.2% TER and +5.5% BLEU and outperforms any other system submitted to the shared-task by a large margin.According to the automatic evaluation metrics used for the task, our system is ranked first among all submission to the shared task.

show abstract

Why Predicting Post-Edition is so Hard? Failure Analysis of LIMSI Submission to the APE Shared Task

Cited by 5 publications

References 3 publications

Findings of the 2015 Workshop on Statistical Machine Translation

Findings of the 2015 Workshop on Statistical Machine Translation

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

Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing

Contact Info

Product

Resources

About