Romanian Language Resources Repository View all resources
- Păiş,Vasile and Ion,Radu and Avram,Andrei-Marius and Mitrofan,Maria and Tufiș,Dan (2021). In-depth evaluation of Romanian natural language processing pipelines. Romanian Journal of Information Science and Technology (ROMJIST), vol 24, no 4, pages 384-401, https://www.romjist.ro/full-texts/paper700.pdf .[Download BibTex]
Models for Stanza, RNNTagger, NLP-Cube, UDPipe, TreeTagger trained on the RRT UD 2.7 corpus. The models were evaluated in the associated paper. Scripts used in training and evaluating the models are available in our GitHub. A working version of the TTL tool is available in the TEPROLIN service repository. For downloading the corpus visit the Universal Dependencies website or directly download UD 2.7 treebanks.