BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Argument Mining from Text for Teaching and Assessing Writing - Dia
 ne Litman\, University of Pittsburgh
DTSTART:20150220T120000Z
DTEND:20150220T130000Z
UID:TALK57551@talks.cam.ac.uk
CONTACT:Tamara Polajnar
DESCRIPTION:The written and diagrammed arguments of students (and the mapp
 ings between them) are educational data that can be automatically mined fo
 r purposes of student instruction and assessment. This talk will illustrat
 e some of the opportunities and challenges in educationally-oriented argum
 ent mining from text. I will first describe how we are using natural proce
 ssing to develop argument mining systems that are being embedded in two ty
 pes of educational technologies: computerized essay grading and computer-s
 upported peer review. I will then present the results of empirical evaluat
 ions of these technologies\, using argumentative writing data obtained fro
 m elementary\, high school\, and university students.\n\nBio: Diane Litman
  is Professor of Computer Science\, Senior Scientist with the Learning Res
 earch and Development Center\, and Co-Director of the Graduate Program in 
 Intelligent Systems\, all at the University of Pittsburgh. She is also a f
 ormer Chair of the North American Chapter of the Association for Computati
 onal Linguistics. Dr. Litman's current research focuses on enhancing the e
 ffectiveness of educational technology through the use of spoken and natur
 al language processing (e.g.\, spoken tutorial dialogue systems\, text sum
 marization for classroom apps\, and argument mining). 
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR