• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  Bookmark and Share
Master's Dissertation
Full name
Deborah Bassi Stern
Knowledge Area
Date of Defense
São Carlos, 2020
Izbicki, Rafael (President)
Prates, Marcos Oliveira
Silva, Diego Furtado
Title in English
Vector representation of texts applied to prediction models
Keywords in English
Natural language processing
Neural networks
Prediction models
Abstract in English
Natural Language Processing has gone through substantial changes over time. It was only recently that statistical approaches started receiving attention. The Word2Vec model is one of these. It is a shallow neural network designed to fit vectorial representations of words according to their syntactic and semantic values. The word embeddings acquired by this method are stateof- art. This method has many uses, one of which is the fitting of prediction models based on texts. It is common in the literature for a text to be represented as the mean of its word embeddings. The resulting vector is then used in the predictive model as an explanatory variables. In this dissertation, we propose getting more information of text by adding other summary statistics besides the mean, such as other moments and quantiles. The improvement of the prediction models is studied in real datasets.
Title in Portuguese
Representações vetoriais de textos aplicados a modelos preditivos
Keywords in Portuguese
Modelos de predição
Processamento de linguagem natural
Redes neurais
Representação vetorial de palavras
Abstract in Portuguese
Processamento de linguagem natural sofreu uma grande mudança com o tempo. Abordagens estatísticas passaram a ganhar atenção apenas recentemente. O modelo word2vec é uma destas. Ele é uma rede neural rasa desenhada para ajustar representações vetoriais de palavras segundo seus valores semânticos e sintáticos. As representações de palavras obtidas por este método são o estado da arte. Este método tem muitas aplicações, como permitir o ajuste de modelos preditivos baseadas em textos. Na literatura é comum um texto ser representado pela média das representações vetorias das palavras que o compõem. O vetor resultante é então incluído como variável explicativa no modelo. Nesta dissertação propomos a obtenção de mais informação sobre o texto através de outras estatísticas descritivas além da média, como outros momentos e quantis. A melhora dos modelos preditivos é estudada com dados reais.
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
DeborahBassiStern.pdf (602.32 Kbytes)
Publishing Date
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2021. All rights reserved.