Abstract

Abstract: Tests like Semantic Verbal Fluency have been used to characterise language in typical and in clinical conditions, like Dementia. For instance, given a sequence of semantically related words, a large number of switches from one semantic class to another has been linked to clinical conditions. In this talk I discuss work on using semantic similarity measures for characterising groups of speakers and how some measures can be used to inform the detection of clinical conditions. In one study this information is used for building classifiers to distinguish healthy controls from clinical cases with early stages of Alzheimer’s Disease and Mild Cognitive Deficits. The results obtained indicate that the classifiers that use these similarity measures outperform those that use a gold standard taxonomy.

Short Bio: Aline Villavicencio is a Reader in Computer Science affiliated to the Federal University of Rio Grande do Sul (Brazil) and also affiliated to the University of Essex (UK). Her research interests include lexical semantics, multilinguality, and cognitively motivated NLP . She received her PhD from the University of Cambridge (UK) in 2001, and held postdoc positions at the University of Cambridge and University of Essex (UK). During 2011-2012 and 2014-2015, she was on sabbatical at the Massachusetts Institute of Technology (USA). She is a current member of the editorial board of the Journal of Natural Language Engineering, the Transactions of the Association for Computational Linguistics, among others, and was Area Chair for NAACL 2018 , for COLING 2018 and for IBERAMIA 2018 , and the Chair for the International Conference on Computational Processing of Portuguese (PROPOR 2018). She is also a regular member of the program committee for the various ACL conferences, and has co-chaired numerous *ACL workshops on Cognitive Aspects of Computational Language Acquisition and on Multiword Expressions. She has co-edited special issues and books dedicated to these topics.