Specialized Machine Translation Using the Microsoft Translator Hub – Customized Models for Language Preservation and Domain Specific Deployment

This talk provides an overview of an enhancement that enables the Microsoft Translator to provide targeted and customizable translation systems. This new system, called the Microsoft Translator Hub, enables personalized, private, and/or crowdsourced translation models to be independently built by companies, communities, and language preservationists.

By way of example, this talk also covers the recent release of Hmong Daw—the first language to be empowered by the Microsoft Translator Hub—including the lessons learned during the Hmong community’s pre-release and post-release usage of the tool for language preservation purposes.

发言人详细信息

Kristin Tolle is director of natural interactions in the Microsoft Research Connections team and a clinical associate professor at the University of Washington College of Medicine. Since joining Microsoft, Kristin has acquired numerous patents and worked for several product teams, including the Natural Language Group, Visual Studio, and the Microsoft Office Excel Team. Prior to Microsoft, Kristin was an Oak Ridge Science and Engineering Research Fellow for the National Library of Medicine and a research associate at the University of Arizona Artificial Intelligence Lab, where she managed the group on medical information retrieval and natural language processing. Her research interests include ubiquitous computing, global public health, contextual computing, natural language processing and machine translation, mobile computing, user intent modeling, and information extraction from large heterogeneous data sources. She earned her PhD in the management of information systems with a minor in computational linguistics.

日期：
演讲者：
Kristin Tolle
所属机构：
Microsoft Research Connections