Romanian Language Resources Repository View all resources
Author(s):
Păiș, Vasile; Ion, Radu; Avram, Andrei-Marius; Mitrofan, Maria; Tufiș, Dan
Research Institute for Artificial Intelligence "Mihai Drăgănescu", Romanian Academy
Stable RELATE URL: https://relate.racai.ro/repository/annotation_models_rrt_2_7
License: CC BY-NC 4.0
Download:
- ud27_nlpcube.zip (337.3 Mb)
- ud27_rnntagger.zip (652.65 Mb)
- ud27_stanza.zip (738.82 Mb)
- ud27_treetagger.zip (1.35 Mb)
- ud27_udpipe.zip (13.08 Mb)
- https://github.com/racai-ai/RoBLARK_evaluation
- https://github.com/racai-ai/TEPROLIN
- http://hdl.handle.net/11234/1-3424
Please include one or more of the following references in your research work:[Download BibTex]
- 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]
Description:
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.