Milan Straka

TL;DR: An update to UDPipe 1.0 (Straka et al., 2016), a trainable pipeline which performs sentence segmentation, tokenization, POS tagging, lemmatization and dependency parsing, which provides models for all 50 languages of UD 2.0.

TL;DR: This overview paper defines the task and the updated evaluation methodology, describes data preparation, report and analyze the main results, and provides a brief categorization of the different approaches of the participating systems.

TL;DR: UDPipe, a pipeline processing CoNLL-U-formatted files, performs tokenization, morphological analysis, part-of-speech tagging, lemmatization and dependency parsing for nearly all treebanks of Universal Dependencies 1.2.

TL;DR: The task and evaluation methodology is defined, how the data sets were prepared, report and analyze the main results, and a brief categorization of the different approaches of the participating systems are provided.

TL;DR: It is found that fine-tuning a multilingual BERT self-attention model pretrained on 104 languages can meet or exceed state-of-the-art UPOS, UFeats, Lemmas, (and especially) UAS, and LAS scores, without requiring any recurrent or language-specific components.