Curva Fin Bloque

Machine Translation Technology

Pangeanic was the first translation company in the world to make commercial use of the statistical machine translation system Moses. Experience now the power of AI applied to Deep Adaptive MT engines: custom machine translation, human-in-the loop, plug-ins and integrations

Nowadays, Pangeanic’s neural machine translation engines are first-of-class and are chosen for data privacy by US government agencies, the European Union and Member States, as well as many  companies that need to process thousands of pages daily at scale – including human-in-the-loop for final publication services.

Pangeanic Machine Translation Technology

Pangeanic
Curva Fin Bloque Negativa

Corporations, businesses and language service providers have benefited from our user-centric flexible approach. Users are in control of their own data and can customize and take ownership of their own machine translation software. Our proprietary Deep Adaptive Machine Translation technology ensures you can impact Machine Learning at different levels, prioritizing your own content and choose how you customize MT engines by domain, by user, by specific jobs.

Machine Translation Language Pairs

PangeaMT was developed upon a large statistical framework in 2010, with quality estimation and re-training.

Statistics worked very well in several related languages (Romance languages and English, German and Scandinavian languages). However, our links to Japanese industry soon provided requests to add Japanese and Chinese to our service portfolio.

In 2011, Pangeanic developed hybrid machine translation services in which were included as part of the system features. In 2017, all our systems were migrated to a new framework based on neural networks and many more language pairs are available as a result of our NTEU project for the EC creating the largest neural machine translation engine farm not pivoting through English.

Machine Translation Language Pairs

Features – No lock-in machine translation services

Use our powerful API to machine translate documents, files or text snippets privately from our own cloud. Choose any of our monthly or annual plans. Retrain and customize your engines at will. We have partner programs for language service providers and plug-ins to major CAT tools (Trados, MemoQ, Memsource, etc.)

With PangeaMT, you can create your own, safe data ecosystem with cloud or on-premises deployments – fast and easy!

Avoid having you locked-in by expensive upgrades year after year

Neural Machine Translation - Our History

It is a general agreement that Neural Machine Translation (NMT) has surpassed Statistical Machine Translation (SMT) in terms of fluency and adequacy when humans read the texts produced by the software. NMT uses a large artificial neural network that resembles what happens in the human brain with thousands of connections. One of the main advantages of NMT is that the context of the translation is much longer than SMT (phrase-level translation). Currently, developers mostly use sequence-to-sequence approaches where the full context of the sentence is taken into account. Accuracy and fluency of the translations increase with the use of NMT. Other advantages of NMT in respect to SMT are that NMT only requires a fraction of the memory needed by SMT and all parts of the NMT models are trained jointly (end-to-end approach) in order to maximize the target translation performance. Pangeanic is at the forefront of research and development of translation technologies incorporating NMT, embedding it in different processes.

Pangeanic has developed and used machine translation for many applications. It has reported successful use cases for many of its clients at industry events like Localization World Barcelona 2011Localization World Paris 2012, Localization World London 2013, as well as numerous TAUS summits in the United States, Europe and in Japan, META Forum Berlin 2013 and Japan Translation Federation.

Pangeanic was also one of the largest donors of training data to TAUS, which in turn provided access to millions of words as training corpus. This enhanced PangeaMT platform and provided our team with the opportunity to experiment further, with millions and millions of aligned sentences. Machine translation became part of company culture since 2009. Since then, machine translation services to corporations and even other translation companies have become part of Pangeanic’s range of services. From 2012 to 2016, Pangeanic has been a member of the EU’s Marie Curie action EXPERT Project, advancing the state-of-the-art with young and experienced researchers.

Neural Machine Translation - Our History. Pangeanic

Machine Translated Documents and Tags (in-line parser)

Another breakthrough is our in-line mark-up parser and full document reconstruction of machine translated documents in other languages. PangeaMT handles tags extremely efficiently. Machine translation systems (as they come from open sources releases) usually produce plain text output because this is also the format they process. PangeaMT implementations at the Spanish Tax Office, news agencies, legal firms require full document translation, which means keeping the format as close to the original as possible (MS Office family formats such as Word, Excel, PowerPoint and others), including layout, image distribution, tables, etc. 

For language professionals using CAT tools, our parser  can identify in-lines without attempting to translate them, and it places them back in the resulting text, too. An in-line placeholder acts first by copying and transferring all XML and code information to a separate module. The translation engine does its work and then places the in-line back into the translated segment. At the time of its release, our in-line parser constituted an innovation well-above the current level of maturity of other well-known systems. 

Please visit our machine translation division website to learn more about PangeaMT features.

Where we are

Europa

Valencia

Oficinas centrales Pangeanics

Av. Cortes Valencianas, 26-5,

Ofi 107

46015 Valencia (Spain)

(+34) 96 333 63 33
[email protected]

London

Flat8, 279 Church Road,
Crystal Palace
SE19 2QQ
United Kingdom
+44 203 5400 256

[email protected]

Madrid

Atrium
Castellana 91
Madrid 28046
Spain
(+34) 91 326 29 33
[email protected]

USA

Boston

One Boston Place
Suite 2600
Boston MA 02108
(617) 621-4084
[email protected]

New York

228 E 45TH St Rm 9E
10017-3337 New York, NY

[email protected]  

Asia

Hong Kong

21st Floor, CMA Building
64 Connaught Road Central
Hong Kong
Toll Free: +852 2157 3950
[email protected]

Tokyo

Ogawa Building 3F

3-37 Kanda Sakuma-cho

Chiyoda-ku, Tokyo

101-0025

[email protected]

Shanghai

Tomson Commercial Building,
Room 316-317
710 Dong Fang Road
Pu Dong, Shanghai 200122, China

[email protected]