Meet up

Learning word embeddings from text

Wednesday, 25th June in London

This meetup was organised by The London Big-O Meetup in June 2014

Overview

Learning word embeddings from text

Classical language modelling consists in assigning probabilities to sentences by factorizing the joint likelihood of the sentence into conditional likelihoods of each word given that word’s context. Neural language models further try to "embed" each word into a low-dimensional vector-space representation that can be learned as the language model is trained. When they are trained on very large corpora, these models can achieve state-of-the-art performance in many applications such as speech recognition or sentence completion.



Piotr Mirowski

Piotr Mirowski is a data scientist who works as a software engineer at Microsoft Bing in London, where he focuses on NLP and deep learning techniques for search query formulation.


Gibbs Sampling: Some Theory and Some Practice



Dominic Steinitz

Dominic Steinitz is a mathematician / statistician / functional programmer who has worked as a statistician in medical research,market research and computer network modelling before moving into running large IT projects in the airline industry and large information security projects in banking.


Who's coming?

Attending Members