README.md

metadata

license: apache-2.0
language:
  - bs
  - bg
  - ca
  - hr
  - cs
  - da
  - nl
  - en
  - et
  - fi
  - fr
  - gl
  - de
  - el
  - hu
  - is
  - it
  - lt
  - lv
  - 'no'
  - pl
  - pt
  - ro
  - sr
  - es
  - sk
  - sl
  - sv
  - tr
  - uk
tags:
  - parliament
inference: false

Multilingual parliamentary model XLM-R-parla

This is the XLM-R-large model additionally pre-trained on texts of parliamentary proceedings. Texts for the additional pre-training come from the ParlaMint corpus and the EuroParl corpus.

The model is a result of the ParlaMint project. The details on the model development are described in the following publication (to be published soon):

Michal Mochtak, Peter Rupnik, Nikola Ljubešić: The ParlaSent Multilingual Training Dataset for Sentiment Identification in Parliamentary Proceedings.