Czech Text Processing with Contextual Embeddings: POS Tagging, Lemmatization, Parsing and NER
This work addresses natural language processing for Czech, an incremental improvement using existing methods on new data.
The paper tackled Czech text processing tasks by evaluating BERT and Flair contextual embeddings on POS tagging, lemmatization, parsing, and NER, achieving state-of-the-art results on multiple corpora.
Contextualized embeddings, which capture appropriate word meaning depending on context, have recently been proposed. We evaluate two meth ods for precomputing such embeddings, BERT and Flair, on four Czech text processing tasks: part-of-speech (POS) tagging, lemmatization, dependency pars ing and named entity recognition (NER). The first three tasks, POS tagging, lemmatization and dependency parsing, are evaluated on two corpora: the Prague Dependency Treebank 3.5 and the Universal Dependencies 2.3. The named entity recognition (NER) is evaluated on the Czech Named Entity Corpus 1.1 and 2.0. We report state-of-the-art results for the above mentioned tasks and corpora.