UDPipe Frysk


This service is freely available. Please respect the CC BY-NC-SA licence of the models – explicit written permission of the authors is required for any commercial exploitation of the system. If you use the service, you agree that data obtained by us during such use can be used for further improvements of this system.


Select Input:
















About

UDPipe Frysk is a web app for lemmatizing, PoS tagging and depdencency parsing of Frisian texts. The lemmatizer/tagger/parser are trained on Frisian text that is annotated according to the guidelines of Universal Dependencies version 2 . We use UDPipe as available via the R package udpipe . UDPipe Frysk is still under develoment. Comments are welcome and can be sent to .


The following people were involved in the development of UDPipe Frysk: Hans Van de Velde (Fryske Akademy, project manager/financing), Wilbert Heeringa (Fryske Akademy, building training corpus/implementation UDPipe Frysk), Gosse Bouma (University of Groningen, building training corpus/advice), Martha Hofman (Fryske Akademy, building training corpus), Eduard Drenth (building web service).


In addition to the lemmatizer/tagger/dependency parser for Frisian, a lemmatizer/tagger/dependency parser for Dutch (LassySmall, compiled by Gosse Bouma and Gertjan van Noord) and English (ParTUT, compiled by Cristina Bosco and Manuela Sanguinetti) is provided. When entering or uploading some text, the appropriate tool is automatically chosen.


Web service

A web service has been developed by Eduard Drenth.

If you want to process a text file 'Frysk.txt' and save the output as a conllu file, give the command:

curl -X POST -H 'Content-Type: text/plain' --data-binary '@Frysk.txt' https://frisian.eu/udpipeservice/udpipe/process/conllu

If you want to process the text 'Praat mar Frysk' and save the output as TSV file, give the command:

curl -X POST -H 'Content-Type: text/plain' --data-binary 'Praat mar Frysk' https://frisian.eu/udpipeservice/udpipe/process/tsv

For bigger texts use the command line script .


System requirements

UDPipe Frysk runs best on a computer with a monitor with a minimum resolution of 1370 x 870 (width x height). The use of (a recent version of) Chrome, Chromium, Edge, Firefox or Opera as a web browser is to be preferred.


How to cite this program

Wilbert Heeringa, Gosse Bouma, Martha Hofman, Eduard Drenth, Jan Wijffels & Hans Van de Velde (2021). POS tagging, lemmatization and dependency parsing of West Frisian, arXiv preprint arXiv:2107.07974. Click here in order to read this paper.


Acknowledgements

The development of this software was made possible by a CLARIAH-Plus project financed by the Dutch Research Council (Grant 184.034.023). We thank Milan Straka and Jana Straková (Charles University, UFAL) for developing UDPipe . We thank Jan Wijffels (BNOSAC) for developing and making available the R package udpipe . In this web app we used glyphs from the Glyphicon Halflings set.


Implementation

Two existing web apps served as examples, namely UDPipe and Linguakit . UDPipe Frysk is implemented as a Shiny app. Shiny was developed by RStudio. This web app uses the following R packages:


  • base

    R Core Team (2017). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. https://www.R-project.org/

  • shiny

    Winston Chang, Joe Cheng, J.J. Allaire, Yihui Xie and Jonathan McPherson (2017). shiny: Web Application Framework for R. R package version 1.0.0. https://CRAN.R-project.org/package=shiny

  • shinyjs

    Dean Attali (2018). shinyjs: Easily Improve the User Experience of Your Shiny Apps in Seconds. R package version 1.0. https://CRAN.R-project.org/package=shinyjs

  • shinyWidgets

    Victor Perrier, Fanny Meyer and David Granjon (2019). shinyWidgets: Custom Inputs Widgets for Shiny. R package version 0.5.0. https://CRAN.R-project.org/package=shinyWidgets

  • shinysky

    Dai ZJ (2019). shinysky: A Set of Shiny Components and Widgets. R package version 0.1.3. https://github.com/AnalytixWare/ShinySky

  • readr

    Hadley Wickham, Jim Hester and Romain Francois (2018). readr: Read Rectangular Text Data. R package version 1.3.1. https://CRAN.R-project.org/package=readr

  • readtext

    Kenneth Benoit and Adam Obeng (2019). readtext: Import and Handling for Plain and Formatted Text Files. R package version 0.75. https://CRAN.R-project.org/package=readtext

  • textreadr

    Rinker, T. W. (2018). textreadr: Read Text Documents into R version 0.9.0. Buffalo, New York. http://github.com/trinker/textreadr

  • openxlsx

    Philipp Schauberger and Alexander Walker (2020). openxlsx: Read, Write and Edit xlsx Files. R package version 4.2.3. https://CRAN.R-project.org/package=openxlsx

  • stringr

    Hadley Wickham (2019). stringr: Simple, Consistent Wrappers for Common String Operations. R package version 1.4.0. https://CRAN.R-project.org/package=stringr

  • cld3

    Jeroen Ooms (2019). cld3: Google's Compact Language Detector 3. R package version 1.2. https://CRAN.R-project.org/package=cld3

  • udpipe

    Jan Wijffels (2019). udpipe: Tokenization, Parts of Speech Tagging, Lemmatization and Dependency Parsing with the 'UDPipe' 'NLP' Toolkit. R package version 0.8.3. https://CRAN.R-project.org/package=udpipe

  • DT

    Yihui Xie, Joe Cheng and Xianying Tan (2019). DT: A Wrapper of the JavaScript Library 'DataTables'. R package version 0.11. https://CRAN.R-project.org/package=DT

  • lattice

    Sarkar, Deepayan (2008) Lattice: Multivariate Data Visualization with R. Springer, New York. ISBN 978-0-387-75968-5

  • igraph

    Csardi G, Nepusz T: The igraph software package for complex network research, InterJournal, Complex Systems 1695. 2006. http://igraph.org

  • ggraph

    Thomas Lin Pedersen (2019). ggraph: An Implementation of Grammar of Graphics for Graphs and Networks. R package version 2.0.0. https://CRAN.R-project.org/package=ggraph

  • ggplot2

    H. Wickham. ggplot2: Elegant Graphics for Data Analysis. Springer-Verlag New York, 2016.

  • textrank

    Jan Wijffels (2019). textrank: Summarize Text by Ranking Sentences and Finding Keywords. R package version 0.3.0. https://CRAN.R-project.org/package=textrank

  • ggwordcloud

    Erwan Le Pennec and Kamil Slowikowski (2019). ggwordcloud: A Word Cloud Geom for 'ggplot2'. R package version 0.5.0. https://CRAN.R-project.org/package=ggwordcloud




Privacy

This app uses cookies that are used to collect data. By using this site you agree to these cookies being set. Google Analytics is used in order to track and report website traffic. See: How Google uses data when you use our partners' sites or apps .


Liability

This app is provided 'as is' without warranty of any kind, either express or implied, including, but not limited to, the implied warranties of fitness for a purpose, or the warranty of non-infringement. Without limiting the foregoing, the Fryske Akademy makes no warranty that: 1) the app will meet your requirements, 2) the app will be uninterrupted, timely, secure or error-free, 3) the results that may be obtained from the use of the app will be effective, accurate or reliable, 4) the quality of the app will meet your expectations, 5) any errors in the app will be corrected.


The app and its documentation could include technical or other mistakes, inaccuracies or typographical errors. The Fryske Akademy may make changes to the app or documentation made available on its web site. The app and its documentation may be out of date, and the Fryske Akademy makes no commitment to update such materials.


The Fryske Akademy assumes no responsibility for errors or ommissions in the app or documentation available from its web site.


In no event shall the Fryske Akademy be liable to you or any third parties for any special, punitive, incidental, indirect or consequential damages of any kind, or any damages whatsoever, including, without limitation, those resulting from loss of use, data or profits, whether or not the Fryske Akademy has been advised of the possibility of such damages, and on any theory of liability, arising out of or in connection with the use of this software.


The use of the app is done at your own discretion and risk and with agreement that you will be solely responsible for any damage to your computer system or loss of data that results from such activities. No advice or information, whether oral or written, obtained by you from the Fryske Akademy shall create any warranty for the software.


Other

The disclaimer may be changed from time to time.