Evaluating Contextualized Embeddings on 54 Languages in POS Tagging, Lemmatization and Dependency Parsing

20 Aug 2019  ·  Milan Straka, Jana Straková, Jan Hajič ·

We present an extensive evaluation of three recently proposed methods for contextualized embeddings on 89 corpora in 54 languages of the Universal Dependencies 2.3 in three tasks: POS tagging, lemmatization, and dependency parsing. Employing the BERT, Flair and ELMo as pretrained embedding inputs in a strong baseline of UDPipe 2.0, one of the best-performing systems of the CoNLL 2018 Shared Task and an overall winner of the EPE 2018, we present a one-to-one comparison of the three contextualized word embedding methods, as well as a comparison with word2vec-like pretrained embeddings and with end-to-end character-level word embeddings. We report state-of-the-art results in all three tasks as compared to results on UD 2.2 in the CoNLL 2018 Shared Task.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Dependency Parsing Universal Dependencies UDPipe 2.0 + mBERT + FLAIR LAS 84.60 # 1
UAS 87.64 # 1