Hessel Haagsma
Computational Linguistics
University of Groningen

About Me

I'm a PhD-candidate at the University of Groningen, working in Johan Bos's Computational Semantics group. My work is part of the Parallel Meaning Bank project, in which I focus on the automatic processing of figurative language phenomena, such as metaphor and idiom. Recently, I’ve been working on the unsupervised disambiguation of potentially idiomatic expressions in context.

I did a BSc in Artificial Intelligence and a MSc in Human-Machine Communication at the Department of AI, as well as a BA in Finnish Language & Culture at the (now sadly defunct) Department of Finno-Ugristics, both at the University of Groningen.

Hessel

Find Me

In the office: Harmonie Building, Room 1311.0435

Via e-mail: hessel.haagsma@rug.nl

On Google Scholar: here

On Github: github.com/hslh

Papers

Angelo Basile, Gareth Dwyer, Maria Medvedeva, Josine Rawee, Hessel Haagsma & Malvina Nissim, 2018. Simply the Best: Minimalist System Trumps Complex Models in Author Profiling. To appear at CLEF 2018. [pdf]

Hessel Haagsma, Malvina Nissim & Johan Bos, 2018. The Other Side of the Coin: Unsupervised Disambiguation of Potentially Idiomatic Expressions by Contrasting Senses. To appear at the LAW-MWE-CxG workshop. [pdf|code]

Daphne Groot, Rémon Kruizinga, Hennie Veldthuis, Simon de Wit & Hessel Haagsma, 2018. PickleTeam! at SemEval-2018 Task 2: English and Spanish Emoji Prediction from Tweets. In Proceedings of SemEval 2018, pp. 454--458. [pdf]

Rik van Noord, Lasha Abzianidze, Hessel Haagsma & Johan Bos, 2018. Evaluating Scoped Meaning Representations. In Proceedings of LREC 2018, pp. 1685—1693. [pdf|code]

Malvina Nissim, Lasha Abzianidze, Kilian Evang, Rob van der Goot, Hessel Haagsma & Martijn Wieling, 2017. Sharing is Caring: The Future of Shared Tasks. In Computational Linguistics 43, no. 4, pp. 897—904. [pdf]

Hessel Haagsma & Malvina Nissim, 2017. A Critical Assessment of a Method for Detecting Diachronic Meaning Shifts: Lessons Learnt from Experiments on Dutch. In Computational Linguistics in the Netherlands Journal 7, pp. 65—78. [pdf|code]

Maria Medvedeva, Hessel Haagsma, & Malvina Nissim, 2017. An Analysis of Cross-Genre and In-Genre Performance for Author Profiling in Social Media. In Proceedings of the 8th International Conference of the CLEF Association, pp. 211—223. [pdf|slides|poster] <- Best Paper Award!

Angelo Basile, Gareth Dwyer, Maria Medvedeva, Josine Rawee, Hessel Haagsma, & Malvina Nissim, 2017. N-GrAM: New Groningen Author-profiling Model. In Working Notes of CLEF 2017 - PAN Lab on Digital Text Forensics. [pdf|slides|shared task results|code]

Johan Bos, Lasha Abzianidze, Johannes Bjerva, Kilian Evang, Hessel Haagsma, Pierre Ludmann, Duc-Duy Nguyen, & Rik van Noord, 2017. The Parallel Meaning Bank: Towards a Corpus of Translations with Deep Semantic Annotation. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, pp. 242—247. [pdf|poster]

Mart Busger op Vollenbroek, Talvany Carlotto, Tim Kreutz, Maria Medvedeva, Chris Pool, Johannes Bjerva, Hessel Haagsma, & Malvina Nissim, 2016. GronUP: Groningen User Profiling. In Working Notes of CLEF 2016 - Digital Text Forensics (PAN), pp. 846—857. [pdf|shared task results]

Hessel Haagsma, 2016. Singleton Detection using Word Embeddings and Neural Networks. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics – Student Research Workshop, pp. 65—71. [pdf|poster]

Hessel Haagsma & Johannes Bjerva, 2016. Detecting Novel Metaphor using Selectional Preference Information. In Proceedings of The Fourth Workshop on Metaphor in NLP, pp. 10—17. [pdf|slides]

Johannes Bjerva, Johan Bos, & Hessel Haagsma, 2016. The Meaning Factory at SemEval-2016 Task 8: Producing AMRs with Boxer. In Proceedings of SemEval-2016, pp. 1070—1075. [pdf|poster|shared task results]

Hessel Haagsma, 2015. Automatic Word Sense Disambiguation for Dutch using Dependency Information. In Computational Linguistics in the Netherlands Journal 5, pp. 15—24. [pdf|slides]

Theses

Hessel Haagsma, 2015. Singleton Detection using Semantic Word Vectors and Neural Networks. MSc thesis, Department of Artificial Intelligence, University of Groningen. [pdf]

Hessel Haagsma, 2014. Interaction between case marking, grammatical role and co-reference in Finnish: a corpus study. BA thesis, Department of Finno-Ugric Languages and Cultures, University of Groningen. [pdf]

Hessel Haagsma, 2013. Grammatical role and word order predict referential form in Finnish: an annotated corpus of Finnish. BSc thesis, Department of Artificial Intelligence, University of Groningen. [pdf]

Talks

Hessel Haagsma & Malvina Nissim, 2017. Can we spot meaning shifts in diachronic representations? At Computational Linguistics in the Netherlands 27 (CLIN27), Leuven, Belgium. [abstract|slides|code]

Teaching

2018/2019 (autumn) - Learning from Data - with Malvina Nissim

2017/2018 (autumn) - Learning from Data - with Malvina Nissim

2017/2018 (autumn) - Shared Task Information Science - with Rik van Noord & Gertjan van Noord

2016/2017 (autumn) - Learning from Data - with Malvina Nissim

2015/2016 (autumn) - Learning from Data - with Malvina Nissim & Johannes Bjerva

Other Activities

Organizing the IWCS 2019 shared task on DRS Parsing - with Lasha Abzianidze, Johan Bos & Rik van Noord

Organizing the CLIN 29 shared task on Cross-Genre Author Profiling for Dutch - with Maria Medvedeva, Malvina Nissim, Walter Daelemans, Tim Kreutz, Martijn Kleppe & Steven Claeyssens

Participated in the PAN17 shared task on Author Profiling - with Angelo Basile, Gareth Dwyer, Maria Medvedeva, Josine Rawee & Malvina Nissim

Participated in the PAN16 shared task on Author Profiling - with Mart Busger op Vollenbroek, Talvany Carlotto, Tim Kreutz, Maria Medvedeva, Chris Pool, Johannes Bjerva & Malvina Nissim

Participated in the CLIN26 shared task on Coreference Resolution for Dutch - with Rob van der Goot & Dieke Oele [code]

Organized the TABU Dag 2016 linguistics conference - with Charlotte Lindenbergh, Steven Gilbers, Anna Pot & Nienke Wolthuis

Participated in the SemEval-2016 shared task on AMR Parsing - with Johan Bos & Johannes Bjerva