I am a computer scientist who works with natural language processing (NLP) and language technology for digital humanities and its underlying disciplines. In my recent research, I have focused on the use of language technology particularly for (1) the automatic detection of semantic change in languages (2) the automatic extraction and structured representation of typological linguistic data from natural language descriptions, and (3) the digitization and accessibility of rich resources on natural languages of the world.
During my PhD, I worked with Grammatical Framework group at University of Gothenburg, and developed resource grammars for six Indo-Iranian languages including Hindi, Urdu, Persian, Punjabi, Nepali, and Sindhi. These grammars are in the form of software libraries and encode different syntactical and lexical aspects of those natural languages.
As a postdoctorate researcher at the Institute of Information Science at Academia Sinica, Taiwan, I worked on a Propbank based semantic role labeling and an information extraction systems for English and Chineese. I was also involved in the French FrameNet project at IRIT, France, where we worked on a FrameNet based semantic role labeling system, and on the extension of the relational structure of English FrameNet.
I am working as a researcher at Språkbanken since 2015. Here, I have been involved in a number of projects most notably in the South Asia as a Linguistic Area, DReaM and Milage. Currently, I am involved in a six year project ChangeIsKey where we are aiming to develop state-of-the-art methods and tools to automatically detect semantic change (over time) in natural languages.
