In this post Pat Nagle, our Project Manager at KantanMT speaks about Neural MT and the importance of using high quality data while training MT engines. He delves deep into the various ways in which KantanMT data can be used in order to get the best translation output. Continue reading
Giulia Mattoni, an Italian Translation Technology student from DCU talks about her experience using Machine Translation for evaluating player support content localization. Giulia’s fascinating view illustrates why this area needs further research, and how she used KantanMT to evaluate MT and post-editing for this type content. Continue reading
Master’s student Ewa Nitoń of the University College London submitted her thesis as part of the MSc degree in Scientific, Technical and Medical Translation with Translation Technology. The following guest article is a reflection on her research concerning the application of Machine Translation in medical context. Ewa was supervised by Teaching Fellow and Lecturer Dr. Emmanouela Patiniotaki and she used KantanMT.com for her MSc research. Continue reading
Dissemination of Machine Translation innovation is a major priority for us at KantanMT. We believe that Academic Partnerships have a huge role to play in furthering the scope of research and innovation in the field of Machine Translation, and as such we have partnered with a number of Universities to help students use the KanataMT platform in a real word scenario.
We are always looking for ways to improve the KantanMT platform, and to keep our finger on the pulse of the KantanMT user experience, we asked one of the students using the platform to answer some questions about the platform.
The United Nations (UN) are big promoters of multilingualism and this week is no exception. The UN Academic Impact (UNAI) and the ELS Educational Services launched a student essay contest to promote international education and multilingualism. Entrants should submit an essay written in one of the six official languages of the UN: Arabic, Chinese, English, French, Russian and Spanish as long as it’s not their native tongue.
The theme of the contest “Many Languages, One World’, focuses on multilingualism in a globalised world and supports communication between all global citizens. The UN is a global organisation, which understands the challenges in making hefty volumes of content available in different languages.
In 2001, Kofi Annan, UN Secretary-General at the time, suggested there was a linguistic imbalance with the UN having a tendency towards English. The reasons behind the imbalance boiled down to high translation costs and a lack of resources.
Ten years later, in 2011, the World Intellectual Property Organization (WIPO) in collaboration with the UN, trained their Moses technology based Machine Translation engine, using approx. 11 years of translated UN documents (2000 – 2012), which were provided by the UN’s Documentation Division (DD). The Tapta4Un was born – a Statistical Machine Translation (SMT) engine for professional UN translators.
The UN had used Google translate and Bing Translator to translate their publicly available documents at first, and with good results. But as data from other organisations was added to those engines, the quality of UN translated documents began to decrease.
The TAPTA engine, built with customised UN training data, provided a much higher quality Machine Translation result and higher BLEU scores compared with google translate. This paved the way for the ‘gText’ project, a global UN project, which is the product of the positive adoption of Machine Translation, tasked with integrating computer aided translation (CAT) tools into the document workflow.
KantanMT allows users to build a customised translation engine with training data that will be specific to their needs. KantanMT are continuing to offer a 14 day free trial to new members. click here>>