Enrico Santus's repositories
Outlier_Detection
Data and code for the experiments in the Outlier Detection task proposed by Camacho-Collados et al.
Thematic_Fit
Data and code for the experiments in: "Measuring Thematic Fit with Distributional Feature Overlap". Enrico Santus, Emmanuele Chersoni, Alessandro Lenci and Philippe Blache. EMNLP 2017
evalution2
This repository contains a library for the EVALuation of Semantic Relations related Tasks
ConceptClassification
This repository contains code to process PDF files and classify their sentences as belonging to one or more concepts.
Excel-Filler
Word+Char CNN to classify one or more columns in an Excel file (easy to use)
Gothic-Bible-Mapper
Code to map the Gothic Bible to other bibles and obtain the scrip transliteration and the IPA transcriptions. An etymological vocabulary is also used to identify Gothic borrowings and cognates in other languages.
MetaphoricChange
Data and code for the experiments in: "German in Flux: Detecting Metaphoric Change via Word Entropy". Dominik Schlechtweg, Stefanie Eckmann, Enrico Santus, Sabine Schulte im Walde and Daniel Hole. CoNLL 2017.
ml-class-assignments
Programming Exercises on http://ml-class.org
mysqldump-to-csv
A quickly-hacked-together Python script to turn mysqldump files to CSV files. Optimized for Wikipedia database dumps.
natural-language-processing
Programming Assignments and Lectures for Stanford's CS 224: Natural Language Processing with Deep Learning
private-kit
Private Kit, an open source privacy preserving system for using personal information
prostate_path
This repository contains the code for the Prostate Pathology Report project, by CSAIL, MIT, and Philips.
text_nn
Text classification models. Used a submodule for other projects.
thematic_update
This repository contains the scripts and data to run the thematic update code.
UnsupervisedHypernymy
Data and code for the experiments in: "Hypernyms under Siege: Linguistically-motivated Artillery for Hypernymy Detection". Vered Shwartz, Enrico Santus and Dominik Schlechtweg. EACL 2017.