BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.4.5//EN TZID:Europe/Paris X-WR-TIMEZONE:Europe/Paris BEGIN:VEVENT UID:0-302@lisn.upsaclay.fr DTSTART;TZID=Europe/Paris:20250917T140000 DTEND;TZID=Europe/Paris:20250917T140000 DTSTAMP:20250912T082208Z URL:https://www.lisn.upsaclay.fr/evenements/less-than-meets-the-eye-repres enting-compounds-in-large-language-models/ SUMMARY:Less than Meets the Eye: Representing Compounds in Large Language M odels DESCRIPTION:Large language models have been successfully used for capturing distinct (and very specific) word usages\, and therefore could provide an attractive alternative for accurately determining meaning in language. Ho wever\, these models still face a serious challenge when dealing with non- literal language\, like that involved in Multiword Expressions (MWEs) such as idioms (make ends meet)\, light verb constructions (give a sigh)\, ver b particle constructions (shake up) and noun compounds (loan shark). MWEs are an integral part of the mental lexicon of native speakers often used t o express complex ideas in a simple and conventionalised way accepted by a given linguistic community. Although they may display a wealth of idiosyn crasies\, from lexical\, syntactic and semantic to statistical\, that repr esents a real challenge for current LLMs\, their accurate integration has the potential for improving the precision\, naturalness and fluency of man y tasks. In this talk\, I will present an overview of how advances in LLMs have made an impact for the identification and modelling of idiomaticity and MWEs. I will concentrate on what models seem to incorporate of idiomat icity\, as idiomatic interpretation may require knowledge that goes beyond what can be gathered from the individual words of an expression (e.g. “ dark horse” as an unknown candidate who unexpectedly succeeds). I will a lso present an initiative to construct a multilingual idiomatic dataset.\n Short Bio\nAline Villavicencio is the Director of the Institute of Data Sc ience and Artificial Intelligence\, University of Exeter\, affiliated to t he  Department of Computer Science\, University of Sheffield (UK)\, is a member of ELLIS and has a Fellowship at the Alan Turing Institute. Before these\, she held academic positions in the Institute of Informatics\, Fede ral University of Rio Grande do Sul\, Brazil (between 2005 and 2021) and i n the School of Computer Science and Electronic Engineering\, University o f Essex\, UK. \nShe 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). She was a Visiting Scholar at the Massachusetts Institute of Technology (USA\, 2011-2012 and 2014-2015)\, at the École No rmale Supé­rieure (France\, 2014)\, an Erasmus-Mundus Visting Scholar at Saarland University (Germany in 2012/2013) and at the University of Bath (UK\, 2006-2009).  \;She held a Research Fellowship from the  \;Br azilian National Council for Scientific and Technological Development (Bra zil\, 2009-2017). She is a member of the editorial board of Computational Linguistics\, TACL and of JNLE. She is the General Chair of EACL 2026 and was the PC Co-Chair of ACL 2022\, CoNLL 2019\, Senior Area Chair for EMNLP 2025\, ACL 2020 and ACL 2019 among others and General co-chair for the 20 18 International Conference on Computational Processing of Portuguese. She was also a member of the NAACL board\, SIGLEX board and of the program co mmittees of various *ACL and AI conferences\, and has co-chaired  \;se veral *ACL workshops on Cognitive Aspects of Computational Language Acquis ition and on Multiword Expressions. Her research interests include lexical semantics\, multilinguality\, multiword expressions and cognitively motiv ated NLP\, and has co-edited special issues and books dedicated to these t opics. CATEGORIES:Séminaires LOCATION:LISN Site Belvédère\, Rue du Belvédère Campus universitaire b ât 507 91405 Orsay\, France X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Rue du Belvédère Campus universitaire bât 507 91405 Orsay\, France;X-APPLE-RADIUS=100;X-TITLE=LIS N Site Belvédère:geo:0,0 END:VEVENT BEGIN:VTIMEZONE TZID:Europe/Paris X-LIC-LOCATION:Europe/Paris BEGIN:DAYLIGHT DTSTART:20250330T030000 TZOFFSETFROM:+0100 TZOFFSETTO:+0200 TZNAME:CEST END:DAYLIGHT END:VTIMEZONE END:VCALENDAR