BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Representing words for NLP (An introduction to Semantic Vector Spa
 ce Models and GloVe) - Nissim Chekroun\, Sidney Sussex College
DTSTART:20191023T181500Z
DTEND:20191023T194500Z
UID:TALK133771@talks.cam.ac.uk
CONTACT:Matthew Ireland
DESCRIPTION:For many tasks in NLP\, choosing the best internal representat
 ion\, which encodes the meaning of each word in some mathematical object\,
  is crucial. In this talk I’ll begin by briefly introducing a couple of 
 simple naïve representation schemes and show how Vector Space Models (VSM
 s) can be used to address their shortcomings. I will then demonstrate how 
 to learn those vector representations\, focusing on a particular method ca
 lled Global Vectors (GloVe). I will derive its mathematical formulation fr
 om the desired properties and compare its performance to other models. Glo
 Ve word embeddings\, and VSMs in general\, are an easy yet effective way t
 o encode meaning\, given a large enough training corpus. They are very ver
 satile: embeddings make it easy to measure similarity between two words\, 
 and they are also useful feature vectors for other NLP systems. Furthermor
 e\, they can be used as the building blocks for sentence or document embed
 dings\, which can then be tested for similarity in the same way. Finally\,
  the same vectors can be used for many projects\, and pre-trained models a
 re available\, eliminating the cost and effort of training.
LOCATION:Wolfson Hall\, Churchill College
END:VEVENT
END:VCALENDAR