The BioNLP Group at Turku Centre for Computer Science (TUCS) has made available an online prototype of a dependency parser of clinical Finnish that is being developed in close cooperation with Lingsoft.
Relies on Lingsoft's core technologies
The dependency parser relies on POS tags and morphological information from Lingsoft's morphological analyzer and constraint grammar parser for Finnish adapted to clinical language, developed and licensed to TUCS by Lingsoft, Inc. The tools are used to tokenize the input text and assign to each word its disambiguated base form and a set of morphological tags. These are used as features in the dependency parser.
Lingsoft took advantage of the adapted clinical-language morphology model when developing a spelling checker for Finnish health-related and clinical texts, currently sold as a Microsoft Office add-in, and marketed to patient journaling software providers.
Morphological Analysis and Constraint Grammar - Powered by Lingsoft®
Copyright ©1986-2018, Lingsoft Ltd.