GHOST Special Session

Embed All The Things!
Neural embedding models for wide variety of problems

Marek Wydmuch Data Scientist@OLX

We have a great pleasure to invite you to the GHOST Special Session on neural embedding models entitled "Embed All The Things! Neural embedding models for wide variety of problems", which will be held by Marek Wydmuch. Marek is currently a Data Scientis at OLX, the world's leading classifieds platform which provides local communities in high-growth markets with online marketplaces.

Word embedding is the collective name for a set of language modeling and feature learning techniques in natural language processing (NLP) where words or phrases from the vocabulary are mapped to vectors of real numbers. Conceptually it involves a mathematical embedding from a space with one dimension per word to a continuous vector space with a much lower dimension.

During the session, we will learn about novel machine learning methods in natural lanaguage processing. The presentation will start with an introduction to word embeddings and standard techniques like word2vec will be presented. Then, we will learn how to use neural embeddings in many different applications (not only in NLP). Novel embedding methods like search2vec, doc2vec and StarSpace will be discussed.

24 May 2018 11:00
126 BT Lecture and Conference Center of Poznań University of Technology