Pangeanic has introduced the beta version of its BERT-based multilingual anonymization software at the 2nd eTranslation Conference.
VALENCIA, VALENCIA, SPAIN, October 14, 2020 /EINPresswire.com/ — Pangeanic today announced [description of momentum or major milestone]. This milestone is a major move for Pangeanic on its mission to "offer specialist translation, content and language solutions to document producers for global use” and part of its deliverables within the Multilingual Anonymization Project MAPA.
“Introducing the first results of our deep learning applied to anonymization to an eager audience of small and medium enterprises, government and institutional representatives is as high an honor as winning the contract. A lot of expectation has been created with the release of a truly multilingual anonymization software that will help Public Administrations, government offices and private companies comply with privacy laws.” says Manuel Herranz, Pangeanic’s CEO.”
The conference was organised by the “Connecting Europe Facility” eTranslation section and took take place as a virtual event due to current covid-19 travel restrictions. The event begun with an online workshop "My Multilingual Services – powered by Artificial Intelligence (AI)", which took place on 13th October 2020 from 2:30 to 4:00 pm CEST as part of the 18th edition of the European Week of Regions and Cities.
The MAPA Project (Multilingual Anonymization for Pubic Administrations) will provide a full data anonymization tool that has its background within Pangeanic’s anonymization software. It supports several approaches to anonymization (anonymization with placeholders, anonymization with gaps, pseudo-anonymization). MAPA generates xml code so that anonymized content can be useful as data – with processing information added. This allows the user to tailor the anonymization to find the right balance between privacy and data utility. The final deliverable will be a docker installer can also be downloaded on the website.
This news comes in the wake of many recent initiatives and accomplishments of the company, including:
• Gathering massive bilingual datasets for machine translation (10Bn)
• Leading the first neural networks-based machine translation grid “all into all” European languages – the NTEU project
• Open-sourcing translation memory language database NEC TM
Pangeanic specialises in human translation services and language technologies, including natural language processing. Its machine translation services are adaptable to users’ terminology and style within minutes with its proprietary machine learning algorithms. Pangeanic guarantees complete language solutions, whether by machine or human.
Source: EIN Presswire