International Webinar on Machine Translation Applications and Challenges (IWMTAC-2022) will be an engaging online event where World’s round and eminent industry and academic expert speakers will deliver the presentation to a large audience who participate by submitting questions, responding to polls, and using other available interactive tools. It is an event held on the using synthetic examples, we develop a novel technique to mine examples from real world data to explore challenges for deployed systems. We use our method to compile an evaluation benchmark spanning examples for four languages from three language families, which we publicly release to facilitate research. 

Features of the webinar

The objective features of webinars are to present a simple, extensible method to mine such examples from real-world text. Our method does not require expansive manuallycurated word lists for each target language, which enables us to discover new kinds of entities that are susceptible to model bias but are not usually thought of this way. Indeed, while we demonstrate its utility with nouns with four target languages, our method is naturally extensible to new language pairs and parts of speech with no change in design