Volltext-Downloads (blau) und Frontdoor-Views (grau)

Pre‑training neural machine translation with alignment information via optimal transport

  • With the rapid development of globalization, the demand for translation between different languages is also increasing. Although pre-training has achieved excellent results in neural machine translation, the existing neural machine translation has almost no high-quality suitable for specific fields. Alignment information, so this paper proposes a pre-training neural machine translation with alignment information via optimal transport. First, this paper narrows the representation gap between different languages by using OTAP to generate domain-specific data for information alignment, and learns richer semantic information. Secondly, this paper proposes a lightweight model DR-Reformer, which uses Reformer as the backbone network, adds Dropout layers and Reduction layers, reduces model parameters without losing accuracy, and improves computational efficiency. Experiments on the Chinese and English datasets of AI Challenger 2018 and WMT-17 show that the proposed algorithm has better performance than existing algorithms.

Download full text files

  • 4818.pdf

Export metadata

Additional Services

Search Google Scholar


Author of HS ReutlingenRätsch, Matthias
Erschienen in:Multimedia tools and applications
Place of publication:Dordrecht
Document Type:Journal article
Publication year:2023
Tag:alignment information; neural machine translation; optimal transport; pre-training
Page Number:21
PPN:Im Katalog der Hochschule Reutlingen ansehen
DDC classes:004 Informatik
Open access?:Nein
Licence (German):License Logo  In Copyright - Urheberrechtlich geschützt