Leo Wanner

Universitat Pompeu Fabra (UPF)


Leo Wanner earned his Diploma degree in Computer Science from the University of Karlsruhe and his PhD in Linguistics from the University of The Saarland. Prior to joining ICREA, he held positions at the German National Centre for Computer Science, University of Waterloo, the University of Stuttgart and the Pompeu Fabra University, Barcelona. As visiting researcher, he was also affiliated with U of Montreal, U of Sydney, U of Southern California's Institute for Information Sciences, U Paris 7, and the Columbia University, New York. Throughout his career, Dr Wanner has been involved in various large scale national, European, and transatlantic research projects. He has published eight books and about 170 refereed journal and conference articles and serves as regular reviewer for a number of high profile conferences and journals.

Research interests

Leo Wanner is working in the field of computational linguistics, teaching the computer how to supply people with information that might be useful to them in their language and how to serve as interpreter between people who do not speak a common language. Leo’s research foci include automatic multilingual report generation, automatic summarization of written material, data-driven parsing, and concept extraction. He is furthermore interested in lexicology and lexicography, and there, in particular, in the recognition, representation and use of lexical idiosyncrasies by both native speakers and learners of a language.

Selected publications

– Ballesteros M, Bohnet B, Mille S & Wanner L 2016, ‘Data-driven deep-syntactic dependency parsing’, Natural Language Engineering, 22, 6, 939 – 974.

– Epitropou V, Bassoukos T, Karatzas K, Karppinen A, Wanner L, Vrochidis S, Kompatsiaris I & Kukkonen J 2016, ‘Environmental data extraction from heatmaps using the AirMerge system’, Multimedia Tools And Applications, 75, 3, 1589 – 1613.

– Espinosa Anke L, Camacho-Collados J, Rodríguez-Fernández S, Saggion H & Wanner L 2016, ‘Extending WordNet with Fine-Grained Collocational Information’, Proceedings of the International Conference on Computational Linguistics (COLING), Osaka, Japan.

– Domínguez M, Farrús M & Wanner L 2016, ‘An Automatic Prosody Tagger for Spontaneous Speech’, In Proceedings of the International Conference on Computational Linguistics (COLING), Osaka, Japan.

– Ballesteros M & Wanner L 2016, ‘A Neural Network Architecture for Multilingual Punctuation Generation’, In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Short paper track, Austin, TX.

– Rodríguez Fernández S, Espinosa Anke L, Carlini R & Wanner L 2016, ‘Semantics-Driven Recognition of Collocations Using Word Embeddings’ In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), Short paper track, Berlin, Germany.

– Rodríguez-Fernández S, Carlini R, Espinosa Anke L & Wanner L 2016, ‘Example-based Acquisition of Fine-grained Collocation Resources’, Proceedings of the International Conference on Linguistic Resources and Evaluation (LREC), Portoroz, Slovenia.

– Domínguez M, Burga A, Farrùs M & Wanner L 2016, ‘Using hierarchical information structure for prosody prediction in content-to-speech applications’, Proceedings of the 8th Speech Prosody Conference, Boston, MA.

Selected research activities

During 2016, Dr. Wanner was also involved as PI and Coordinator in several large scale European R&D projects.