BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Internal seminar - new PhD students - New NLIP PhDs
DTSTART:20171117T120000Z
DTEND:20171117T130000Z
UID:TALK94714@talks.cam.ac.uk
CONTACT:Anita Verő
DESCRIPTION:1) Distributional Semantic Models Suited To Morphologically Ri
 ch Languages\n\nPaula Czarnowska\n\nDuring my MPhil I worked on a modified
  version of the Skip-gram model in which the target-word’s contexts were
  defined as words connected to it through a dependency relation. The model
  associated meaning representations with all three: target-words\, context
 -words and dependency labels which allowed it to learn important interacti
 ons between those during training. In the next three years I intend to con
 tinue working in the area of distributional semantics. More specifically\,
  I plan to work on cross-linguistically applicable semantic models\, with 
 a focus on morphologically rich languages.\n\n—————————
 ————————————————————————
 —————\n\n2) Multimodality and Language Acquisition\n\nChris Davi
 s\n\nMy MPhil focused on differentiating visual input in the context of se
 mantic similarity and predicting brain activity. My PhD will investigate m
 ultimodal models for language acquisition.\n\n—————————
 ————————————————————————
 —————\n\n3) Predicting the limits of the Zone of Proximal Develo
 pment: a vector based approach\n\nRussell Moore\n\nAccording to Vygotsky\,
  the `Zone of Proximal Development' (ZPD) is the set of learning tasks tha
 t can be successfully completed by a student\, with assistance from a huma
 n or from non-human scaffolding.\nIn this study we use a vector-based enco
 ding of student achievement as the input to a machine-learning classificat
 ion task which aims to predict the limits of a student's ZPD at a given po
 int in their learning career.  We evaluate this encoding with data from 1\
 ,000 eligible users taken from a large-scale online learning environment. 
  The model in this context is able to predict whether a question falls ins
 ide a student's ZPD\, with a combined F1 score of 0.80.
LOCATION:FW11\, Computer Laboratory
END:VEVENT
END:VCALENDAR