Donghui zhang microsoft

Zhang worked at Microsoft headquarters starting in , playing a key role in developing the Microsoft PhotoStory product. Zhang led the Digital Ink research. Her research team was active in the handwriting recognition research area, such as math equation recognition, chemical formula recognition, and East Asian language recognition. In addition to publishing at top conferences, her team collaborated with product teams to transfer the developed technologies and systems into a number of Microsoft products, e.

Zhang founded the Software Analytics group at MSRA in , and led the team to conduct cutting-edge research and technology innovation in an interdisciplinary area that spans across big data, machine learning, systems, and software engineering. In recent years, Dr. Zhang received her Ph. Method and system for semantically labeling strings and providing actions based on semantically labeled strings.

Method and system for providing restricted actions for recognized semantic categories. Application program interfaces for semantically labeling strings and providing actions based on semantically labeled strings. Method, system, and apparatus for converting dates between calendars and languages based upon semantically labeled strings. Method, system, and apparatus for converting currency values based upon semantically labeled strings. Method, system, and apparatus for converting numbers based upon semantically labeled strings.

Mechanism for downloading software components from a remote source for use by a local software application. Providing contextually sensitive tools and help content in computer-generated documents. Method and system for associating actions with semantic labels in electronic documents. Methods and system for recognizing names in a computer-generated document and for providing helpful actions associated with recognized names. Leveraging markup language data for semantically labeling text strings and data and for providing actions based on semantically labeled text strings and data.

Automatic context sensitive language correction and enhancement using an internet corpus. WOA1 en. Gesture keyboard input of non-dictionary character strings using substitute scoring. Improved message recognition employing integrated speech and handwriting information. Speech recognition system which selects one of a plurality of vocabulary models.