Nimdzi Finger Food is the bite-sized and free to sample insight you need to fuel your decision-making today
A specific use case worth exploring in this regard is MT for User Generated Content (UGC). Because of the speed with which UGC (comments, feedback, reviews) is being created and the corresponding costs of its professional translation, many organizations turn to MT.
Popular examples of such companies are Skype (in addition to text translation, Microsoft developed the Automatic Speech Recognition (ASR) for audio speech translation in Skype) and Facebook. The social network is aiming to solve the challenge of fine-tuning each system relating to a specific language pair, using neural machine translation (NMT) and benefiting from various contexts for translations.
One solution that tackles this issue is the technology developed by Language I/O. The company’s SaaS platform translates chats, emails, and other UGC instantaneously via MT. It takes into account the client's glossaries and TMs, selects the best MT engine output and then improves on the results using cultural intelligence and/or human linguists who compare machine translations post-facto to ensure that their MT Optimizer engine learns over time.
The solution is powered by Language I/O machine learning technology coupled with an MT aggregator and a proprietary glossary imposition layer. Because the integrated MT engines are constantly learning in their own right, the MT Optimizer needs to continuously improve its ability to select the best MT engine for each translation request based on:
This tech plugs into Salesforce, Oracle, and Zendesk – the CRM platforms where support agents already work. They are also providing their APIs so that anyone with UGC can use the service (not necessarily just customer service personnel).
One of the main reasons for implementing machine translation (MT) into localization workflows is that it saves money. And time. This time, let’s focus on money. In particular, cost savings.
How one implements Machine Translation (MT) in their lives? Let’s dig further into how this nice scheme can be applied to a Machine Translation Post Editing (MTPE) workflow. Here’s a common 4-step way.
School is back in session! In this episode, Michael interviews a panel of localization professors—Max Troyer, Jon Ritzdorf and Jan Grodecki—about how they are preparing students for the future of localization. They discuss how curriculum should both ride the wave of current technology as well as teach students traditional critical skills. Other topics include the […]