The monolingual Slovene RoBERTa (A Robustly Optimized Bidirectional Encoder Representations from Transformers) model is a state-of-the-art model representing words/tokens as contextually dependent word embeddings, used for various NLP tasks. Word embeddings can be extra...

Trilingual BERT (Bidirectional Encoder Representations from Transformers) model, trained on Croatian, Slovenian, and English data. State of the art tool representing words/tokens as contextually dependent word embeddings, used for various NLP classification tasks by fin...

converts a table of letters into CMI format

A collection of classes that represent archaeological data. This package provides a set of S4 classes that extend the basic matrix data type (absolute/relative frequency, presence/absence data, co-occurrence matrix, etc.) upon which package developers can build subclass...

<p>Pie Model for Classical French, for Part-of-Speech and Morphology tags (CATTEX2009-max).</p> <p>Trained on a corpus of Classical French Theatre.</p> <p><strong>More information</strong>:</p> <p>- <em>corpus</em>: Camps, Jean-Baptiste, & Cafiero, Florian. (2019). Styl...

<p>This script is associated with the paper Geomorphometric methods for tumuli recognition and extraction from high resolution LiDAR DEMs submitted to Sensors. It work in conjunction with the data available at https://doi.org/10.5281/zenodo.3628795 and a DEM available b...

This artifact contains all the source code and data related to the SANER 2020 paper titled "Essential Sentences for Navigating Stack Overflow Answers". These files are based on <a href="https://github.com/ualberta-smr/saner2020-artifactpage">https://github.com/ualberta-...

Jupyter notebooks to work with data from the State Library of South Australia.

Experiments and examples relating to Trove's 'Diaries, letters, and archives' zone.