Apertium linguistic data for Romanian
Find a file
2025-04-05 18:11:46 +02:00
.github/workflows Add workflows 2022-05-21 13:44:38 +02:00
dev/testvoc find-duplicates.sh 2022-08-07 22:19:49 +02:00
tagger-data Update .gitignore 2025-04-05 08:31:22 +02:00
test setup apertium-regtest 2021-07-19 19:33:35 -05:00
.gitattributes Update/add .gitignore and .gitattributes 2018-03-17 01:38:50 -05:00
.gitignore Update .gitignore 2025-04-05 08:31:22 +02:00
apertium-ron.pc.in Remove lib from data-only pkg-config 2016-02-01 20:23:16 +00:00
apertium-ron.post-ron.dix Postgen format 2024-03-16 18:11:19 +01:00
apertium-ron.ron.acx Fixes, pronouns 2019-03-12 23:46:49 +01:00
apertium-ron.ron.dix în privința 2024-01-04 11:45:12 +01:00
apertium-ron.ron.rlx OFTC, http -> https, url fixups 2021-05-27 12:04:23 +02:00
apertium-ron.ron.tsx Data and scripts for tagger training, updated README 2025-04-04 09:05:58 +02:00
AUTHORS Release 1.0.0 2019-11-10 16:53:21 +00:00
autogen.sh fr-ro split into fra, ron, fra-ron (with fra-stuff from fr-es). TODO: ron->fra had an old t1x (no t2x/t3x), currently used as the t1x here but needs to output chunks (or modes need changing to assume t1x 2015-01-05 20:17:38 +00:00
ChangeLog fr-ro split into fra, ron, fra-ron (with fra-stuff from fr-es). TODO: ron->fra had an old t1x (no t2x/t3x), currently used as the t1x here but needs to output chunks (or modes need changing to assume t1x 2015-01-05 20:17:38 +00:00
configure.ac setup apertium-regtest 2021-07-19 19:33:35 -05:00
COPYING fr-ro split into fra, ron, fra-ron (with fra-stuff from fr-es). TODO: ron->fra had an old t1x (no t2x/t3x), currently used as the t1x here but needs to output chunks (or modes need changing to assume t1x 2015-01-05 20:17:38 +00:00
Makefile.am setup apertium-regtest 2021-07-19 19:33:35 -05:00
modes.xml Data and scripts for tagger training, updated README 2025-04-04 09:05:58 +02:00
NEWS fr-ro split into fra, ron, fra-ron (with fra-stuff from fr-es). TODO: ron->fra had an old t1x (no t2x/t3x), currently used as the t1x here but needs to output chunks (or modes need changing to assume t1x 2015-01-05 20:17:38 +00:00
README Data and scripts for tagger training, updated README 2025-04-04 09:05:58 +02:00
README.md Data and scripts for tagger training, updated README 2025-04-04 09:05:58 +02:00
ron.prob add ron, makefile todo 2014-11-19 15:18:25 +00:00
tagger.supervised.make Rebuild dic if TSX changes 2025-04-05 18:11:46 +02:00
tagger.unsupervised.make Rebuild dic if TSX changes 2025-04-05 18:11:46 +02:00

Romanian: apertium-ron

This is an Apertium monolingual language package for Romanian. What you can use this language package for:

  • Morphological analysis of Romanian
  • Morphological generation of Romanian
  • Part-of-speech tagging of Romanian

Requirements

You will need the following software installed:

  • lttoolbox (>= 3.5.0)
  • apertium (>= 3.6.0)
  • vislcg3 (>= 1.3.0)

If this does not make any sense, we recommend you look at: https://apertium.org

Compiling

Given the requirements being installed, you should be able to just run:

$ ./autogen.sh
$ make

If you're doing development, you don't have to install the data, you can use it directly from this directory.

If you are installing this language package as a prerequisite for an Apertium translation pair, then do (typically as root / with sudo):

# make install

You can give a --prefix to ./autogen.sh to install as a non-root user, but make sure to use the same prefix when installing the translation pair and any other language packages.

If any of this doesn't make sense or doesn't work, see https://wiki.apertium.org/wiki/Install_language_data_by_compiling

Testing

If you are in the source directory after running make, the following commands should work:

$ echo "o casă" | apertium -d . ron-morph
^o/o<ij>/un<det><ind><f><sg><nom>/îl<prn><pro><p3><f><sg><nom>$ ^casă/casă<n><f><sg><nom><ind>$

$ echo "o casă" | apertium -d . ron-tagger
^un<det><ind><f><sg><nom>$ ^casă<n><f><sg><nom><ind>$ 

Tagger model training

To train the tagger model, do one of the following:

Supervised training:

$ make -f tagger.supervised.make

Unsupervised training

$ make -f tagger.unsupervised.make

For details on the corpora used in training, check the corpora information.

For more information, see https://wiki.apertium.org/wiki/Tagger_training

Files and data

For more information

Help and support

If you need help using this language pair or data, you can contact:

See also the file AUTHORS, included in this distribution.