/TheNationalRapporteur

The National Rapporteur Challenge - 2nd edition of Hackathon for Good

Primary LanguageJupyter NotebookGNU General Public License v3.0GPL-3.0

The National Rapporteur Challenge

2nd edition of the Hackathon for Peace, Justice and Security

TEXT MINING AND RELATIONSHIP EXTRACTION TO INFORM POLICY RECOMMENDATIONS AND INCREASE IMPACT

The Dutch National Rapporteur on Trafficking in Human Beings and Sexual Violence against Children reports independently on the nature and extent of human trafficking and sexual violence against children in the Netherlands, and on the effects of the government policies put in place. The National Rapporteur raises public awareness for these phenomena, and makes policy recommendations aimed at preventing and combating human trafficking and sexual violence against children.

Problem: Every person is entitled to protection against exploitation. Every child is entitled to protection of his or her sexual integrity. Shortcomings in that protection cannot only have a seriously harmful effect for the individual, but also have a disruptive effect on society as a whole.

The main objective of the National Rapporteur on Trafficking in Human Beings and Sexual Violence against Children is to combat these issues by reporting independently on the nature and extent of human trafficking and sexual violence against children in the Netherlands, and on the effects of the government policies put in place. The National Rapporteur pursues this objective by conducting thorough independent research and by publishing reports in which he makes specific recommendations to the issues addressed.

Over the past two decades, a wealth of information has been compiled. These reports and recommendations are all stored in a publication database online. Although the database and the documents are searchable, search results only show the report in which the information is found. In order to contribute to a better knowledge and understanding of this subject matter, information in this database needs to become more accessible.

Outcome: To write an algorithm that detects all relevant information in the publication database, and gives a complete and comprehensible overview of relevant paragraphs, graphics and other subject matter in the search results. This display of information will contribute to a better understanding of both phenomena and the ongoing developments, a greater awareness of the policies and recommendations, and perhaps even lead to new insights.

Datasets

(Please note most of these documents are in Dutch.)

The National Rapporteur’s publication database

All the publications of the database

Deep Learning Resources

If you are developing a deep neural network based solution, you can use the free GPUs provided by either Google Colab or Kaggle. Here are the instructions for both:

Google Colab:

Go to Google Colab and start a new notebook. You can use the instructions in this notebook to upload your datasets and work on them in Colab. When you need to use GPUs to train your models, switch GPU on under Edit --> Notebook settings. This notebook shows you an example of training a model built in TensorFlow using a GPU.

Kaggle:

Go to Kaggle and create a user profile. Then, go to Kernels --> New Kernel. A blank notebook opens up, and you can write your code in here. You will see on the right side of the notebook an option to turn on the GPU. On the top right side of your notebook, you will see a symbol that looks like a cloud with an arrow on it. You can click on this to upload your data to Kaggle.

Other options:

If you have a Google Cloud, or Amazon Web Services, or Paperspace account, etc, you can use one of these to train your models.