Magahi: apertium-mag

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

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

Requirements

You will need the following software installed:

• autoconf
• automake
• pkg-config
• lttoolbox (>= 3.5.1)
• apertium (>= 3.6.1)
• vislcg3 (>= 1.3.1)
• hfst (>= 3.15.1)
• lexd (>= 0.0.1)

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

Compiling

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

$ autoreconf -fvi
$ ./configure
$ make

You can use ./autogen.sh instead of autoreconf and ./configure if you're compiling from source.

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 use a --prefix with ./configure 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 "साधू जङगल में राजा देखलो" | apertium -d . mag-morph
^साधू/sādhū<n><nom>/sādhū<n><obl>/sādhū<n><obl>$ ^जङगल/jaṅgal<n><nom>/jaṅgal<n><obl>$ ^में/me<v><pres><inf><o_p2><hi>/meṃ<post>$ ^राजा/rāj<v><hab>/rāj<v><pres><s_p2>/rājā<n><nom>/rājā<n><obl>/rājā<v><pres><inf>/rājā<n><obl>$ ^देखलो/dekh<v><past><s_p3>/dekh<v><past><inf><o_p2><hi>$^./.<sent>$

$ echo "साधू जङगल में राजा देखलो" | apertium -d . mag-tagger
^sādhū<n><nom>$ ^jaṅgal<n><obl>$ ^me<v><pres><inf><o_p2><hi>$ ^rāj<v><hab>$ ^dekh<v><past><s_p3>$^.<sent>$

Files and data

• apertium-mag.mag.lexd - Morphotactic dictionary
• apertium-mag.mag.twol - Morphophonological rules
• apertium-mag.mag.rlx - Constraint Grammar disambiguation rules
• apertium-mag.post-mag.dix - Post-generator
• mag.prob - Tagger model
• apertium-mag.mag.spellrelax - Typographical variance rules
• apertium-mag.mag.udx - Mappings from Apertium tags to Universal Dependencies features
• modes.xml - Translation modes
• apertium-mag.Lat-Dev.lexd - Transliteration transducer
• apertium-mag.Lat-Dev.twol - More rules for the transliteration transducer

For more information

• https://wiki.apertium.org/wiki/Installation
• https://wiki.apertium.org/wiki/apertium-mag
• https://wiki.apertium.org/wiki/Using_an_lttoolbox_dictionary
• https://wikis.swarthmore.edu/Magahi
• https://wikis.swarthmore.edu/Magahi/Transducer
• https://wikis.swarthmore.edu/Magahi/Final_Project

Help and support

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

• Mailing list: [email protected]
• IRC: #apertium on irc.oftc.net (irc://irc.oftc.net/#apertium)

See also the file AUTHORS, included in this distribution.

Disclaimer

We are not experts in Magahi. We didn't have access to Magahi speakers or very good reasources for this project. There is a very good chance this material is wrong. If you are a Magahi speaker and want to improve this, please feel free to contact the authors at [email protected] or submit a pull request or issue. If you are a Magahi speaker and want it taken down for any reason, we would be happy to oblige.