Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Digitální knihovna V...arrow_drop_down
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Word2vec Models with Added Context Information

Authors: Šůstek, Martin;

Word2vec Models with Added Context Information

Abstract

This thesis is concerned with the explanation of the word2vec models. Even though word2vec was introduced recently (2013), many researchers have already tried to extend, understand or at least use the model because it provides surprisingly rich semantic information. This information is encoded in N-dim vector representation and can be recall by performing some operations over the algebra. As an addition, I suggest a model modifications in order to obtain different word representation. To achieve that, I use public picture datasets. This thesis also includes parts dedicated to word2vec extension based on convolution neural network.

Tato práce se zabývá porozuměním word2vec modelů. Přestože tyto modely vznikly nedávno (2013), staly se velmi populárními. Učením těchto modelů lze obdržet vektorovou reprezentaci slov v~N-dimenzionálním prostoru reálných čísel. Pomocí operací nad těmito vektory je možné určit sémantické vazby mezi slovy. Dále se práce snaží o rozšíření představených modelů za účelem jiné reprezentace slov. K tomuto účelu je navrženo využití obrazové informace. Taktéž je diskutována možnost použití konvolučních neuronových sítí ve spojitosti s poskytnutím odlišné kontextové informace.

A

Country
Czech Republic
Related Organizations
Keywords

Umělá inteligence, Softmax, Language Modelling, Zpracování přirozeného jazyka, Word Embeddings, Vnořování slov, NLP, Semantic Similarity, LM, Neuronové sítě, Sémantická podobnost, AI, Konvoluční neuronové sítě, Word2vec, Artificial Inteligence, Convolution Neural Network, CNN, Artificial Neural Networks, Natural Language Processing

Powered by OpenAIRE graph
Found an issue? Give us feedback