Sara Stymne

This page will no longer be updated, please visit my new webpage instead.

I have left Linköping University. Currently I am doing a postdoc at Uppsala University.

I was a researcher at the Department of computer and information science at Linköping University until 2012. I received a PhD in Computational Linguistics from Linköping University in 2012, with the thesis Text Harmonization Strategies for Phrase-Based Statistical Machine Translation. I received a Licentiate degree in Computational Linguistics in 2009, and a Master's degree in Cognitive science in 2006, both from Linköping University.

My main supervisor is Lars Ahrenberg and my secondary supervisor is Joakim Nivre. I am affiliated with the Swedish Graduate School of Language Technology (GSLT). I spent the autumn 2010 and spring 2009 at Xerox Research Centre Europe in Grenoble, France.

Research interests

My main research interest is machine translation. I am interested mainly in statistical translation, but also in hybrid methods.

I am investigating how pre- and postprocessing of training and translation data can improve phrase-based statistical machine translation (PBSMT). The main focus for my licentiate thesis was on compounds in Germanic languages, particularly in Swedish and German. Currently I am investigating other pre- and postprocessing strategies for PBSMT, targeting phenomena such as definitie nouns, reordering, and agreement.

Software and resources

Blast is a tool for error analysis of machine translation output.

In my earlier work I investigated verb frame divergences between Swedish and English and how to handle these in an MT-system. In order to do this I developed a bilingual HPSG grammar (BiTSE) for Swedish and English which can be used both for parsing and generation.