|search externally:||Google Scholar, Springer, CiteSeer, Microsoft Academic Search, Scirus , DBlife|
I am a postdoc at Google Research in Zurich, working with Keith Hall and other smart people on summarization, semi-supervised learning, learning from (very) noisy data, and graph-based methods for NLP.
I did my PhD at EML Research (now HITS) while being a student at TU Darmstadt. My thesis is about sentence fusion, that is about how to generate a single novel sentence from the dependency structures of a set of related sentences. First, a new tree is generated (see the EMNLP'08 paper) and then it is linearized (see the ACL'07 and NAACL'09 papers). The same method has been used for sentence compression with encouraging results (see the INLG'08 paper). Unfortunately I did not find time to brush up the code and put a nice package online but I am happy to share the code as it is and help setting everything up, I've done it already and it worked! Other topics I was very much interested in during my PhD are discourse and information structure and coherence (see the ESSLLI'06 workshop paper and contact me if you are interested in the more detailed journal paper on this topic). You can download the thesis from here.
I spent three months at Yahoo! Research in Barcelona in 2008, working on how summarization algorithms can be adapted to the domain of financial news (see the EACL'09 paper). In 2007 I spent half a year at Xerox Research in Grenoble working on structured pdf-to-xml conversion.
NLP at Google
as author at 4th Russian Summer School in Information Retrieval (RuSSIR), Voronezh 2010,