English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The attribute-value representation of documents used in text mining provides a natural framework for classifying or clustering documents based on their contents. In the context of machine learning algorithms, the attribute-value representation of documents is often accomplished by using the bag-of-words approach. Since every word in the document could be treated as an attribute, such an approach is characterized by yielding very high dimensional data. In fact, the representation of documents has a crucial influence on how well some learning algorithms (either supervised or unsupervised) can perform. As one of the main contributions of this work, a framework to efficiently decomposing text into words by using the bag-of-words approach, as well as reducing the dimensionality of the representation generated, is presented. This framework makes text accessible to most machine learning algorithms for it only requires data to be described as a vector of fixed dimensionality. In order to illustrate the framework proposed, a computational tool was implemented. This tool by, among other things, reducing the dimensionality of the text representation can lead to an improvement in the performance of the machine learning techniques being applied. The types of machine learning algorithms employed were either supervised or unsupervised, depending on the problem in hand. For instance, supervised learning algorithms can be applied whenever the documents have labels preassigned, whereas unsupervised learning algorithms are often applied to unlabelled data. For the case of unsupervised learning, in order to evaluate if a given cluster corresponds to a certain concept, this work takes another approach by using inductive learning techniques. For example, with this approach one could understand how the system represents and reasons about the acquired knowledge. Explanation facilities are required both for user acceptance of the solution generated by the system, and for the purpose of understanding whether the reasoning is sound.

"Uma abordagem para pré-processamento de dados textuais em algoritmos de aprendizado"