Federico Nanni's Projects
Mapping a variable-length sentence to a fixed-length vector using BERT model
Computational Psychology Shared Task organized with NAACL 2022
Materials from my UniMannheim course (2017->2019)
Slides and Jupyter Notebooks for the Computational Text Analysis at the Political Science Dept. University of Mannheim
2018 Computational Text Analysis Notebooks, University of Mannheim
A Flexible Deep Learning Approach to Fuzzy String Matching
Method for extracting entity mentions, inlink and outlink statistics from a MediaWiki XML Dump
Neural Language Models for Historical Research
Machine Learning / Natural Language Processing / Information Retrieval
Introduction to Data Science for Biomedical Scientists
A series of short scripts for creating a dataset of news from the Internet Archive archived version of a newspaper website
A few scripts for using the Entity Linker TagMe, starting from a Wikipedia Dump.
REL: Radboud Entity Linker
A bot tweets the people, things and places that Matteo Salvini mentions in offensive or defiant tweets
Quick and dirty way of establishing if the structure of a web archived page in the Internet Archive has changed substantially over time.
Host repository for The Turing Way: a how to guide for reproducible data science
A few scripts to get out useful stuff from the TREC Car dataset.
Implementation of various methods for trec-car
Analysing Turing publications and outputs from publishers and other data sources