Czech Text Processing with Contextual Embeddings: POS Tagging,\n Lemmatization, Parsing and NER

2019/09/08 by Milan Straka, Straka, Milan, Jana Straková +3
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Semantic Web and Ontologies #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1909.03544

openalex publication_date 2019/09/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Contextualized embeddings, which capture appropriate word meaning depending\non context, have recently been proposed. We evaluate two meth ods for\nprecomputing such embeddings, BERT and Flair, on four Czech text processing\ntasks: part-of-speech (POS) tagging, lemmatization, dependency pars ing and\nnamed entity recognition (NER). The first three tasks, POS tagging,\nlemmatization and dependency parsing, are evaluated on two corpora: the Prague\nDependency Treebank 3.5 and the Universal Dependencies 2.3. The named entity\nrecognition (NER) is evaluated on the Czech Named Entity Corpus 1.1 and 2.0. We\nreport state-of-the-art results for the above mentioned tasks and corpora.\n

Citations

• Long Short-Term Memory
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation

Related

• Evaluating Contextualized Embeddings on 54 Languages in POS Tagging, Lemmatization and Dependency Parsing
• Prague Dependency Treebank -- Consolidated 1.0
• Some Like It Small: Czech Semantic Embedding Models for Industry Applications
• Automatic Extraction of Subcategorization Frames for Czech
• PAMPO: using pattern matching and pos-tagging for effective Named Entities recognition in Portuguese