Compounds, such as chocolate cake and time sink can be defined as the formation of a new lexeme by adjoining two or more lexemes. They are studied extensively in linguistic literature and are enjoying more and more attention in the field of Natural Language Processing (NLP). One intriguing aspect of compounds is the fact that the relation between the two constituents is not expressed overtly. For example, the relation between knife and its modifiers in the compounds cheese knife and kitchen knife is very different and world knowledge is needed to determine the exact reading. Moreover, compounding is a very productive word formation process.
English-speaking children can create novel compounds in spontaneous speech from a very young age (Clark, 1981). As a consequence, compounds are ideal vehicles for creative thought.
In this seminar, an overview of recent work Prof Lonneke Van Der Plas undertook in collaboration with several colleagues and students regarding the automatic interpretation and generation of compounds will be presented.
Lonneke van der Plas is head of the Computation, Cognition and Language group at the Idiap research institute in Martigny, and Associate Professor in Language Technology, in affiliation with the University of Malta. She previously held a junior-professorship at the University of Stuttgart, and a postdoc position at the University of Geneva. She earned a PhD from the University of Groningen and an MPhil from the University of Cambridge. She has been leading several research projects under H2020, Erasmus+, and the German Research Foundation, and was a visiting fellow at the University of Zurich, the University of Melbourne, and Shanghai Jiao Tong University. She has over 50 publications in the field of natural language processing, more in particular on the following topics: multi-lingual natural language processing, vector-based semantics, and computational creativity.