BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Leveraging non-expert semantic intuitions to support multilingual 
 NLP - Olga Majewska\, PhD student in Computational Linguistics\, Faculty o
 f Modern and Medieval Languages and Linguistics
DTSTART:20191114T130000Z
DTEND:20191114T143000Z
UID:TALK134626@talks.cam.ac.uk
CONTACT:Anne Helene Halbout
DESCRIPTION:The recent advances in Natural Language Processing have greatl
 y increased the capacity of automatic systems to understand human language
 . However\, they rely on the availability of large quantities of data\, an
 d still struggle with many language-related tasks which humans perform int
 uitively on an everyday basis. Making subtle meaning distinctions requires
  rich\, fine-grained lexical-semantic and conceptual knowledge. Although a
 utomatic lexical acquisition systems promise to overcome the challenge of 
 creating deep lexical resources manually from scratch\, they depend on the
  availability of gold standard datasets for evaluation purposes\, which is
  still very limited in most languages of the world. Verbs pose a particula
 r challenge for NLP systems due to their complex linguistic properties. Ac
 ting as sentence pivots\, they encode crucial information about the struct
 ural and semantic relationships between the elements of the clause. This i
 s why accurate\, nuanced analysis and representation of their meaning is e
 specially important for NLP systems to get closer to human levels of langu
 age understanding.\n\nFast but reliable creation of semantic resources cou
 ld boost and support multilingual NLP\, eliminating the bottleneck of reso
 urce scarcity in the majority of the world's languages\, and this project 
 aims to facilitate this by developing methodology designed to speed up the
  resource creation process and allow its unlimited extension to diverse la
 nguages. It explores methods for obtaining verb classifications alternativ
 e to manual lexicographic work by leveraging semantic intuitions of non-ex
 pert native speakers. By examining humans' complex\, intuitive word simila
 rity judgments in different languages and encoding them in computer-readab
 le form\, the study explores how meaning relations are organised in the se
 mantic space in the brain and provides insights to support further develop
 ment of representation learning models and their ability to capture fine-g
 rained semantic distinctions present in the mental lexicon.
LOCATION:Room 326\, Raised Faculty Building\, MML\, Sidgwick Avenue\, Camb
 ridge\, CB3 9DA
END:VEVENT
END:VCALENDAR