Pretraining for Neural Machine Translation

Dear Colleagues,

There has been a wealth of research over the past several years on self-supervised pre-training for natural language processing tasks, which aims at transferring the knowledge of large-scale unlabeled data to downstream tasks with labeled data. Despite its success in other understanding and generation tasks, self-supervised pretraining is not a common practice in machine translation (MT).

The purpose of this Special Issue is to understand and improve pretraining for neural machine translation. Researchers in the field are invited to contribute their original and unpublished works. Topics of interest include but are not limited to:

• Inclusion of external knowledge (e.g., parallel data and entity information) into pretraining for machine translation;
• Multimodal (e.g., speech and image) pretraining for machine translation;
• New techniques (e.g., prompt learning) and architectures to better incorporate pretraining into machine translation;
• Automatic metrics to better assess the benefits of pretraining for machine translation that cannot be measured by the BLEU metric (e.g., discourse analysis);
• Identification of the limitations of current pretraining for machine translation;

Usage of pretraining for different translation tasks, including document-level translation, entity translation, and automatic post-editing; Efficient training of massive pretrained models.

Dr. Zhaopeng Tu
Dr. Longyue Wang
Dr. Xing Wang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Information is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.