UNIOR NLP Research Group's repositories
italian-dodiom-corpus
Data used to assess the quality of Italian Crowdsourced Idiom Corpus: Dodiom
collaboration-pt-it
General repository for collaboration pt-it
paideia_sentiment_analysis
Repository per il corso "Sentiment analysis per le Scienze Sociali", tenutosi durante l'Edizione 2022 della Scuola Estiva sul Metodo e la Ricerca Sociale
TBX-Converter
Conversion of CSV into TBX format
TRADISAN
TRADISAN REPO
Unior-NLP-PAN2020_Profiling-Fake-News-Spreaders
UniOR NLP at PAN20 - Profiling Fake News Spreaders on Twitter
DialectBot
A telegram based chatbot for crowdsourcing geo-referenced voice recordings of Italian dialects
George_Floyd_MT_EV
This repo contains the data used to evaluate neural machine translation (EN-IT) in the journalistic domain and the results from the experiments
melld
Repository for MELLD
MWSA20
The repository contains the BiLSTM that participated in the Monolingual Word Sense Alignment (MWSA) shared task across dictionaries as part of the GLOBALEX 2020
Onto_C_VMWEs
This repository contains the linguistic resource described in 'Ontology-based formalisation of Italian Clitic Verbal MWEs: an Approach for Supporting Machine Translation'
PILLAR_Corpus
The PILLAR (Parallel ItaLian engLish ARchaeological) Corpus is an Italian-English domain parallel corpus composed of bi-texts from the archaeological domain in the form of brochures, leaflets, guides and websites.
SMACH-corpora-CheriDesCO
Corpora developed during the SMACH project