Computational Morphology with HFST

This open educational resource can be used as self-study material or as a classroom tutorial. It demonstrates how Helsinki Finite-State Technology (HFST) tools can generate finite-state morphologies. Through practical exercises, students will learn how to use finite-state methods to develop a morphology for a language. This online course is suitable as a complement to a more theory or linguistics-oriented course on morphology.

Erik Axelson developed a Jupyter Notebook interactive version based on an earlier version of the Computational Morphology course taught by Mathias Creutz and Senka Drobac in the Master’s programme 'Linguistic Diversity and Digital Humanities' at the University of Helsinki.

Learning Outcomes

After successfully completing the course, learners will be able to:

- Explain the basic theory of finite-state automata and transducers,

- Design morphological lexica using finite-state technology,

- Write morpho-phonological rules in a finite-state framework,

- Describe the diversity of morphological structures in different languages and apply them when designing computational morphology models.

Author(s)

Erik Axelson

Role: Jupyter code developer of course material

Department of Digital Humanities / The Language Bank of Finland (FIN-CLARIN)

Faculty of Arts, University of Helsinki

Helsinki, Finland

Description of the Training Materials

(Sub)discipline, Topic, Language(s)	computational morphology, finite-state methods English
Keywords	morphology, weighted finite-state networks, two-level rules, xfst, lexc, twolc
URL (s) to Resource	The course is accessible at https://notebooks.csc.fi. Logging into the service requires a Haka or CSC account or visitor account via the CSC/SAFMORIL helpdesk. Entry in CLARIN-FIN: http://urn.fi/urn:nbn:fi:lb-2021053003 Lectures available on Github: https://github.com/hfst/compmorph-course/tree/v1.0
Resource URL Type	http://urn.fi/urn:nbn:fi:lb-2021053001
CLARIN Language Resources	HFST: http://urn.fi/urn:nbn:fi:lb-20140730183 Kielipankki morphologies: http://urn.fi/urn:nbn:fi:lb-2018041703
Structure and Duration	The course comprises seven lectures, based on the original course, with assignments. The solutions to the assignments are unavailable since the original course is still lectured each year.
Target Audience	MA students in linguistics or digital humanities
Expertise (Skill) Level	Intermediate/advanced level Prerequisites include: Basic ICT skills Fundations of general linguistics Basic knowledge of and programming experience are desirable
Facilities Required	Jupyter software Python packages hfst-dev Graphviz
Format	Self-study course containing seven lectures implemented as Jupyter notebooks. Tutorial-type lectures with assignments at the end.
Course(s) in which the training material was used	The training material is taught as part of the “Computational Morphology” (LDA-T302) by Mathias Creutz in the Master’s programme Linguistic Diversity and Digital Humanities at the University of Helsinki for 5 ECTS.
Licence and (re)use	CC BY 4.0: https://creativecommons.org/licenses/by/4.0/
Creation Date	First GitHub repository commit, Nov 29, 2018
Last Modification Date	A stable release was made on 25 June 2021

Experience with Using CLARIN Resources in Teaching

Students appreciated the availability of XFST and TWOL tools through the Python application interface. It facilitates learning and makes integrating morphological analysis and generation as part of larger natural language processing software easy.

Cite this Work

Axelson, Creutz, Drobac (2019). Computational Morphology with HFST – an adaptation of the teaching material of the course 'Computational Morphology' taught by Mathias Creutz in the Master’s programme 'Linguistic Diversity and Digital Humanities' at the University of Helsinki. [Learning material]. Language Bank of Finland. Accessible at http://urn.fi/urn:nbn:fi:lb-2021053001.

Contact Information

Teachers who reuse and adapt this training material can share their feedback via training [at] clarin.eu (training[at]clarin[dot]eu).