Skip to content

tupini07/ensemble-learning-applied-to-record-linkage

Repository files navigation

soweego: ensemble learning applied to record linkage

This repository contains the latex code, as well as supporting scripts, for my master thesis at University of Trento, for the master course in Data Science.

The pdf version of the thesis can be seen here. The PDF document has links but these don't work in Github's PDF viewer (at least at the time I'm writing this). So if you want to clik on them you'll need to download the PDF and open it manually.

The thesis is based on the work done by the author on the Wikidata/soweego project. Soweego also has a project page on wikimedia.

The development of this work was partly supported by this wikimedia foundation grant.

Files and folders

  • graphics - contains the images/graphs used in the thesis
  • presentation - contains a single org mode file which is the presentation I used as supporting material during the defence of my dissertation
  • scripts - contains various scripts used to generate some of the graphics, as well as a jupyter notebook in which some statistics of the results are generated and compared.

The rest of the files are used by TeX to render the final PDF.

About

Ensemble learning applied to record linkage for linking Wikidata entities with external sources.

Topics

Resources

Stars

Watchers

Forks