|Date||Jun 03, 2011|
|Title||Semantic Role Labeling. Generalizing Lexical Features using Selectional Preferences.|
Semantic Role Labeling (SRL) consists of detecting basic event structures such as ``who'' did ``what'' to ``whom'', ``when'' and ``where''. From a linguistic point of view, the task corresponds to identifying the semantic arguments filling the roles of the sentence predicates. The identification of such event frames holds potential for significant impact in many NLP applications, such as Information Extraction, Question Answering, Summarization and Machine Translation.
Associate Professor at the Technical University of Catalonia (UPC) since 2000. PhD. in Computer Science (UPC 1999; awarded the UPC prize for doctoral dissertations in Computer Science). His research focuses on Machine Learning methods for Natural Language structure prediction problems, including syntactic and semantic parsing, and statistical machine translation. He has 80+ papers in Natural Language Processing and Machine Learning journals and conferences. He has been Program Committee member of the major conferences in the area and Program Co-chair of several conferences, including CoNLL, SemEval, EAMT, EMNLP and the forthcoming EACL-2012. Additionally, he has been organizer of several international evaluation tasks at Senseval/SemEval and CoNLL shared tasks. He has served as guest editor of three special issues at Computational Linguistics, Language Resources and Evaluation and the Journal of Natural Language Engineering. He acts as officer of the ACL SIG on Natural Language Learning (SIGNLL) since 2007. He has participated in 6 EU funded projects and 12 Spanish government funded projects, acting as the UPC principal researcher in several of them.