Parsing/home

Background

An experimentation environment for data-driven dependency parsing is maintained for NLPL under the coordination of Uppsala University (UU). Initially, the software and data are commissioned on the Norwegian Abel supercluster.

Preprocessing Tools

• REPP Tokenizer (English and Norwegian)

Additionally, a variety of tools for sentence splitting, tokenization, lemmatization, et al. are available through the NLPL installations of the Natural Language Processing Toolkit (NLTK) and the spaCy: Natural Language Processing in Python tools.

Parsing Systems

• The Uppsala Parser
• UDPipe
• Stanford Graph-Based Parser by Tim Dozat

Training and Evaluation Data

• Universal Dependencies v2.0–2.5
• Semantic Dependency Parsing