BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Semantic (Vector) Representations  of Word Senses\, Concepts and E
 ntities  and their Applications - Jose Camacho-Collados (Sapienza Universi
 ty of Rome)
DTSTART:20170420T100000Z
DTEND:20170420T110000Z
UID:TALK71799@talks.cam.ac.uk
CONTACT:Mohammad Taher Pilehvar
DESCRIPTION:A considerable amount of research has lately been conducted on
  developing neural architectures for learning vector representations of wo
 rd forms (i.e.\, word embeddings). However\, they have clear limitations w
 hen it comes to deep language understanding as they conflate different mea
 nings of a word into a single representation and consequently are unable t
 o accurately model semantics of individual word senses. A field of researc
 h has tried to address this issue with word representations by breaking th
 em into those of their individual meanings. In this presentation I will gi
 ve an overview of current representation techniques with a special emphasi
 s on knowledge-based representations and NASARI (http://lcl.uniroma1.it/na
 sari/)\, our recently developed multilingual representation of concepts an
 d entities. Finally\, I will briefly present some of its most successful a
 pplications to date\, namely semantic similarity\, word and named entity d
 isambiguation\, sense clustering\, domain labeling and text classification
 .\n\nBio: Jose Camacho Collados is a Google Doctoral Fellow and PhD studen
 t at Sapienza University of Rome (http://wwwusers.di.uniroma1.it/~collados
 ). His research focuses on Natural Language Processing and on the area of 
 lexical and distributional semantics in particular. Jose co-organized a tu
 torial on “Semantic Representations of Word Senses and Concepts” at AC
 L 2016 (http://acl2016.org/index.php?article_id=58) and an EACL 2017 works
 hop on "Sense\, Concept and Entity Representations and their Applications"
  (https://sites.google.com/site/senseworkshop2017/). He is additionally co
 -organizing a SemEval shared task on multilingual and cross-lingual semant
 ic similarity (http://alt.qcri.org/semeval2017/task2/). His background edu
 cation includes an Erasmus Mundus Master in Natural Language Processing an
 d Human Language Technology and a 5-year BSc degree in Mathematics.
LOCATION: SR-24\, English Faculty Building\, 9 West Road (Sidgwick Site)
END:VEVENT
END:VCALENDAR