ILSP Neural NLP Toolkit
The ILSP Neural NLP toolkit for Greek currently integrates modules for segmentation, POS tagging, lemmatization, dependency parsing, chunking, named entity recognition and text classification. The toolkit is based on language resources including web crawled corpora, word embeddings, large lexica, and corpora manually annotated at different levels of linguistic analysis.
You can use this service to process any TXT document in UTF-8 encoding and obtain the output in either JSON format or in CSV file format.
According to the processing steps followed by the service, the output includes annotations on the level of sentence (Sentence ID, Sentence), token (Token ID, Token, Token Start, Token End), lemma, part of speech (Upos and Features according to Universal PoS & Features Tagset, Xpos according to XPoS ILSP Tagset), dependency relation (Relation and Head ID) according to Universal Dependency Relations Tagset, named entity (Named Entity, Named Entity Type according to ILSP Neural NER Tagset, Named Entity Score), chunks (Chunk and Chunk Type according to ILSP Neural Toolkit Chunk Tagset) and the thematic category in which the whole text is classified into (Text Classification according to ILSP Neural Text Classification Tagset). See the Output Annotation Schema field below for more information on the respective tagsets.
For technical reasons, the file submitted for processing may be split into smaller files, and so will the output.
This service is seamlessly integrated into the CLARIN:EL infrastructure's workflows, providing users with convenient and easy access as a web service. You can use this service by clicking the "Use" button on this page or by accessing it through the CLARIN:EL processing services page. Read less Prokopidis, Prokopis (2021, July 18). ILSP Neural NLP Toolkit. Version 3.0.1. [Software (Tool/Service)]. CLARIN:EL. http://hdl.handle.net/11500/CLARIN-EL-0000-0000-67B2-3 Prokopidis, Prokopis (2021, July 18). ILSP Neural NLP Toolkit. [Software (Tool/Service)]. CLARIN:EL. http://hdl.handle.net/11500/CLARIN-EL-0000-0000-67D6-B
The SSH Open Marketplace is maintained and will be further developed by three European Research Infrastructures - DARIAH, CLARIN and CESSDA - and their national partners. It was developed as part of the "Social Sciences and Humanities Open Cloud" SSHOC project, European Union's Horizon 2020 project call H2020-INFRAEOSC-04-2018, grant agreement #823782.