• Corpus ID: 249204419

A Quality Estimation and Quality Evaluation Tool for the Translation Industry

@inproceedings{Murgolo2022AQE,
  title={A Quality Estimation and Quality Evaluation Tool for the Translation Industry},
  author={Elena Murgolo and Javad Pourmostafa Roshan Sharami and Dimitar Shterionov},
  booktitle={European Association for Machine Translation Conferences/Workshops},
  year={2022}
}
With the increase in machine translation (MT) quality over the latest years, it has now become a common practice to integrate MT in the workflow of language service providers (LSPs) and other actors in the translation industry. With MT having a direct impact on the translation workflow, it is important not only to use high-quality MT systems, but also to understand the quality dimension so that the humans involved in the translation workflow can make informed decisions. The evaluation and… 
View on ACL
aclanthology.org
3 Citations
Background Citations
1

3 Citations

Tailoring Domain Adaptation for Machine Translation Quality Estimation

The method first trains a generic QE model and then fine-tunes it on a specific domain while retaining generic knowledge, showing a significant improvement for all the language pairs investigated, better cross-lingual inference, and a superior performance in zero-shot learning scenarios as compared to state-of-the-art baselines.

Poor Man’s Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference

This work defines the problem of metric estimation (ME) where one predicts the automated metric scores also without the reference and shows that even without access to the reference, the model can estimate automated metrics at the sentence-level.

Proceedings of the 23rd Annual Conference of the European Association for Machine Translation, EAMT 2022, Ghent, Belgium, June 1-3, 2022

The current state of OPUS-MT, the project on open neural machine translation and the challenges that the team tries to tackle with multilingual NLP, transfer learning and data augmentation are discussed.

6 References

Automatic Annotation of Machine Translation Datasets with Binary Quality Judgements

An automatic method is presented for the annotation of (source, target) pairs with binary judgements that reflect an empirical, and easily interpretable notion of quality.

A Study of Translation Edit Rate with Targeted Human Annotation

A new, intuitive measure for evaluating machine-translation output that avoids the knowledge intensiveness of more meaning-based approaches, and the labor-intensiveness of human judgments is examined, which indicates that HTER correlates with human judgments better than HMETEOR and that the four-reference variants of TER and HTER correlate withhuman judgments as well as—or better than—a second human judgment does.

Bleu: a Method for Automatic Evaluation of Machine Translation

This work proposes a method of automatic machine translation evaluation that is quick, inexpensive, and language-independent, that correlates highly with human evaluation, and that has little marginal cost per run.

eSCAPE: a Large-scale Synthetic Corpus for Automatic Post-Editing

eSCAPE is presented, the largest freely-available Synthetic Corpus for Automatic Post-Editing released so far, and consists of millions of entries in which the MT element of the training triplets has been obtained by translating the source side of publicly-available parallel corpora, and using the target side as an artificial human post-edit.

chrF: character n-gram F-score for automatic MT evaluation

The proposed use of character n-gram F-score for automatic evaluation of machine translation output shows very promising results, especially for the CHRF3 score – for translation from English, this variant showed the highest segment-level correlations outperforming even the best metrics on the WMT14 shared evaluation task.

A. study

  • C. Laymon
  • Medicine, Psychology
    Predication and Ontology
  • 2018
The results of this trial will provide information on the feasibility of the TwiCs design to facilitate multiple trials of potential interventions for children with ADHD, and the acceptability, clinical and cost effectiveness of two potential interventions to ADHD stakeholders including service providers.