Towards a Gamified System to Improve Translation for Online Meetings

Translation of online meetings (e.g., Skype conversations) is a useful feature that can help users to understand each other. However translations can sometimes be inaccurate or they can miss the context of the discussion. This is for instance the case in corporate environments where some words are used with special meanings that can be obscure to other people. This paper presents the prototype of a gamified application that aims at improving translations of and for online meetings. In our system, users play to earn points and rewards – and they try to propose and vote for the most accurate translations in context. Our system uses various techniques to split conversations in various semantically coherent segments and label them with relevant keyphrases. This is how we extract a description of the context of a sentence and we use this context to: (i) weight users' expertise and their translation (e.g., an AI specialist is more likely than a lay person to give a correct translation for a sentence about deep learning) (ii) map the various translations of words and phrases and their context, so that we can use them during online meetings.