Segment level quality estimation builds new competitive business models for MT projects
KantanMT today announced the release of its breakthrough quality estimation technology, KantanAnalytics™. KantanAnalytics generates quality estimation scores for automated translations generated by a KantanMT engine. These scores will help Project Managers predict the cost and schedule of a Machine Translation project
, helping them provide more transparency in managing these projects for their clients.
KantanAnalytics, which has been co-developed with the CNGL Centre for Global Intelligent Content (Dublin City University, Ireland) assigns a quality estimation score for each automated translation generated by a KantanMT engine. Expressed as a percentage – this predicts the score a human translator would likely assign as to the utility of the translation. Segments with higher scores have proven to require considerably less post-editing.
“Machine Translation quality estimation is a game-changer for the Localisation industry,” said Tony O’Dowd, “Using KantanAnalytics our members can predict post-editing effort and cost – something that has proved elusive previously. KantanAnalytics creates new business model opportunities for our members and their clients.”
KantanAnalytics generates a detailed project management report, similar to the well-known and industry standard “fuzzy match” report. This report provides segment details, their quality estimation scores and summarises this into an easy to use format. Project Managers can view this report from within the Project Dashboard on the KantanMT.com platform or download it directly to into Microsoft Excel.
Members of KantanMT.com under the ‘Enterprise Plan’ can avail of this technology from the 30th October.
What is KantanMT™?
KantanMT is a cloud-based implementation of Moses statistical Machine Translation technology. Leveraging the power and flexibility of the cloud, KantanMT effortlessly scales to generate a high-quality, low-cost Machine Translation platform for small-to-medium sized Localisation Service Providers.
CNGL is a collaborative academia-industry research centre dedicated to the development of advanced global content processing technologies. The CNGL research centre combines the expertise of its more than 150 investigators at four universities: Trinity College Dublin (lead institute), Dublin City University, University College Dublin and University of Limerick, as well as that of its industry partners to produce technologies with significant economic and societal impact.