CLARIN Knowledge Centre for Systems and Frameworks for Morphologically Rich Languages (SAFMORIL)

SAFMORIL brings together researchers and developers in the area of computational morphology and its application during language processing. The focus of SAFMORIL is actual, working systems and frameworks based on linguistic principles and providing linguistically motivated analyses and/or generation on the basis of linguistic categories. Such systems are relevant in particular for languages with rich morphologies, e.g. Nordic and Baltic languages (such as Finnish, Swedish, Norwegian, Latvian, Lithuanian as well as the Sámi languages) and more generally Fenno-Ugric languages, Inuit languages, Canadian First Nation languages and Babylonian languages. We offer online courses for developing and teaching morphologies, tokenizers and spell-checkers, a repository for storing morphologies, and an environment for creating tokenizers and spell-checkers. SAFMORIL serves linguists and computational linguists developing and adapting morphologies as well as digital humanities scholars and computer scientists processing language data. If you have any questions, contact us via the SAFMORIL Helpdesk (safmoril@kielipankki.fi).

Morphology Systems and Frameworks

• Morphology-based annotation services
  • Sparv – online annotation tool for text in several languages
  • Open Morphology – word form analysis for several languages (some also with hyphenation, spelling, synonyms and translations)
• Morphology processing and building services
  • Mylly – a tool for analyzing and visualizing data sets (including tools for compiling morphologies)
• Morphology teaching services
  • FinlandSwedishOnline
  • GiallaLT ICALL
• Morphologies and software
  • GiallaLT environment – development environment for morphologies and morphology-based tools
  • HFST – compilation and runtime software (with some source morphologies)
• Morphology in Language Research Literature
  • Google Scholar: Morphology, Language and Linguistics

Tutorials

• How to make computer tools for your language (by GiellaLT at CLARINO)
• Guidelines for Semi-Automated Development of Simplified Two-Level Morphology (by Kimmo Koskenniemi at FIN-CLARIN)
• Online Tutorial for XFST-based Morphology Development (by Erik Axelson, Kimmo Koskenniemi and Mathias Creutz at UHEL)
• Online Tutorial for Morphology Construction (developed by Jack Rueter at FIN-CLARIN)
• Online Tutorial for Developing Morphology-based Tools (by UHEL and CSC at FIN-CLARIN)

Getting started

Introduction to some of the services provided by the K Centre member institutions:

• Giallatekno Resources
• Kielipankki – The Language Bank of Finland

Documentation of the services:

• GiellaLT documentation
• Kielipankki Mylly user guide (platform for processing and analyzing language data)

Standards

Standards recommended:

• CLARIN-D

Collaborators

Experts collaborating with the K Centre on morphologically complex languages:

• Prof Antti Arppe (University of Alberta)
• Prof Kimmo Koskenniemi (University of Helsinki)
• Prof Inguna Skadina (University of Latvia)
• Prof Trond Trosterud (University of Tromsø)
• Dr Harald Hammarström (Uppsala University)
• Dr Krister Lindén (University of Helsinki)
• Dr Tommi Pirinen (Hamburg Zentrum for Sprachkorpora)
• Dr Jouna Pyysalo (University of Helsinki)
• Dr Jack Rueter (University of Helsinki)
• Dr Miikka Silfverberg (University of Helsinki)
• Dr Andrius Utka (Vytautas Magnus University)
• MA Sjur Moshagen (University of Tromsø)
• MA Aleksi Sahala (University of Helsinki)
• MSc Erik Axelson (University of Helsinki)

Related Sites

• CLARIN Knowledge Centre for Computer-Mediated Communication and Social Media Corpora (CKCMC)
• CLARIN Knowledge Centre for South Slavic languages CLASSLA)
• Czech CLARIN Knowledge Centre for Corpus Linguistics (CorpLingCz)
• CLARIN K-Centre DANSK – DANish helpdeSK (DANSK)
• CLARIN Knowledge Centre for Digital and Public Textual Scholarship (DiPText-KC)
• CLARIN Knowledge Centre for Dutch (K-Dutch)
• CLARIN K-Centre for Natural Language Processing in Greece (NLP:EL)
• CLARIN Knowledge Centre for Polish Language Technology (PolLinguaTec)
• CLARIN Knowledge Centre for the Science and Technology of the Portuguese Language (PORTULAN)
• Spanish CLARIN Knowledge Centre (Spanish-K-centre)
• CLARIN Knowledge Centre for Treebanking (Treebanking)

Supported by CLARIN Centres

The K Centre operates as a distributed virtual centre supported by CLARIN member institutions such as:

• FIN-CLARIN:
  • University of Helsinki, Finland: Online courses for developing morphologies, Helpdesk
  • CSC, Finland: Computing environment for tools and online courses
•  CLARINO
  • University of Tromsø, Norway: Proofing tools, Morphology and computational linguistics, Language repository
• CLARIN-LV:
  • University of Latvia: Special knowledge about Latvian
• CLARIN-LT:
  • Vytautas Magnus University, Lithuania: Knowledge of corpus linguistics and natural language processing methods for Lithuanian

If your institution wishes to join our effort to provide high-quality morphological processing tools, please get in touch.

FAQ

FAQ will be compiled from questions and answers acquired via helpdesk / issue tracker.

Contact

The Knowledge Centre is coordinated by the University of Helsinki through its SAFMORIL helpdesk (safmoril@kielipankki.fi). There will also be an issue tracker available for asking questions and reporting bugs, feature requests etc.

CLARIN Certificate of Recognition