BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Computational Models of the Influence of Context on Sentence Accep
 tability - Shalom Lappin\, University of Gothenburg
DTSTART:20200206T110000Z
DTEND:20200206T120000Z
UID:TALK138892@talks.cam.ac.uk
CONTACT:Qianchu Liu
DESCRIPTION:We study the influence of context on sentence acceptability. F
 irst we compare the crowd source acceptability\nratings of sentences judge
 d in isolation\, with a relevant context\, and with an irrelevant context.
  Our results\nshow that context induces a cognitive load for humans\, whic
 h compresses the distribution of ratings. Moreover\,\nin relevant contexts
  we observe a discourse coherence effect which uniformly raises acceptabil
 ity. We then\ntest unidirectional and bidirectional neural language models
  for their ability to predict acceptability ratings.\nThe bidirectional mo
 dels give very promising results\, with the best model achieving a new sta
 te-of-the-art\nfor unsupervised acceptability prediction. The two sets of 
 experiments provide insights into the cognitive\naspects of sentence proce
 ssing\, and central issues in the computational modelling of text and disc
 ourse. (Joint work with Jey Han Lau\, The University of Melbourne\; Carlos
  Armendariz\, Queen Mary University of London\; Matthew Purver\, Queen Mar
 y University of London\; and Chang Shu\,University of Nottingham Ningbo Ch
 ina)
LOCATION:GR04\, Faculty of English\, 9 West Rd (Sidgwick Site)
END:VEVENT
END:VCALENDAR