BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:‘Profit factory’ and ‘bathroom break’: How to analyse comp
 ounds and how to predict their emergence - Lonneke van der Plas (Universit
 y of Malta)
DTSTART:20190918T110000Z
DTEND:20190918T120000Z
UID:TALK128485@talks.cam.ac.uk
CONTACT:James Thorne
DESCRIPTION:Compounds can be defined as the formation of a new lexeme by a
 djoining two or more lexemes (Bauer\, 2003:40). They are studied extensive
 ly in linguistic literature and are enjoying more and more attention in th
 e field of Natural Language Processing (NLP). Compounding is a very produc
 tive word formation process. English-speaking children can create novel co
 mpounds in spontaneous speech from a very young age (Clark\, 1981). As a c
 onsequence\, compounds are a very common word type\, but many occur with a
  very low token count. The high productivity of compounds makes compositio
 nal approaches to automatic processing indispensable. Also\, it raises que
 stions about the processes that underlie the generation of novel compounds
 . \n\nI will give an overview of recent work we undertook that harvests pa
 rallel corpora as indirect supervision for two tasks: compound identificat
 ion\, and bracketing of compounds. I will then discuss the potential of co
 mpounds as vehicles for creative thought and present some experiments that
  aim to predict novel compounds.\n\n\nReferences\n\nBauer\, L. 2003. Intro
 ducing Linguistic Morphology\, 2nd edn.\, Washington\, DC: Georgetown Univ
 ersity Press. \n\nClark\, E. V. (1981). Lexical innovations. How children 
 learn to create new words. In W. Deutsch (Ed.)\, The child's construction 
 of language\, London: Acad. Press.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR