Merge branch 'main' into devel

clarin-eric · Dec 30, 2024 · ffffe2f · ffffe2f
2 parents 645bdf5 + f0d7ee9
commit ffffe2f
Show file tree

Hide file tree

Showing 8 changed files with 20 additions and 10 deletions.
diff --git a/.github/actions/ParlaMintValidate/validate.sh b/.github/actions/ParlaMintValidate/validate.sh
@@ -72,7 +72,7 @@ for parla in $(jq -r '.[]' <<< $1 ); do
   fi
 
   echo "::warning:: TMP restore taxonomy"
-  git checkout Corpora/Taxonomies/ParlaMint-taxonomy*
+  git checkout Build/Taxonomies/ParlaMint-taxonomy*
   git checkout ${DATADIR}/ParlaMint-$parla/ParlaMint-taxonomy*
 done
 

diff --git a/Build/Taxonomies/taxonomy-translation-include.tsv b/Build/Taxonomies/taxonomy-translation-include.tsv
@@ -15,6 +15,7 @@ fi	ParlaMint-FI
 fr	ParlaMint-BE
 fr	ParlaMint-FR
 gl	ParlaMint-ES-GA
+he	ParlaMint-IL
 hr	ParlaMint-HR
 hu	ParlaMint-HU
 is	ParlaMint-IS
@@ -26,6 +27,7 @@ nl	ParlaMint-BE
 nl	ParlaMint-NL
 pl	ParlaMint-PL
 pt	ParlaMint-PT
+sk	ParlaMint-SK
 sl	ParlaMint-SI
 ro	ParlaMint-RO
 sr	ParlaMint-RS

diff --git a/Build/Taxonomies/taxonomy-translation-responsibility.tsv b/Build/Taxonomies/taxonomy-translation-responsibility.tsv
@@ -12,6 +12,7 @@ eu	ParlaMint-ES-PV
 fi	ParlaMint-FI
 fr	ParlaMint-FR
 gl	ParlaMint-ES-GA
+he	ParlaMint-IL
 hr	ParlaMint-HR
 hu	ParlaMint-HU
 is	ParlaMint-IS
@@ -22,6 +23,7 @@ nb	ParlaMint-NO
 nl	ParlaMint-NL
 pl	ParlaMint-PL
 pt	ParlaMint-PT
+sk	ParlaMint-SK
 sl	ParlaMint-SI
 ro	ParlaMint-RO
 sr	ParlaMint-RS

diff --git a/Makefile b/Makefile
@@ -2,7 +2,7 @@
 
 ##$PARLIAMENTS: Space separated list of country codes
 #Parliaments for V4.1
-PARLIAMENTS = AT BE BG CZ DK EE ES ES-CT ES-GA ES-PV FI FR GB GR HR HU IS IT LV NL NO PL PT SE SI TR BA RS UA
+PARLIAMENTS = AT BE BG CZ DK EE ES ES-CT ES-GA ES-PV FI FR GB GR HR HU IS IT LV NL NO PL PT SE SI TR BA RS UA IL
 
 ##$JAVA-MEMORY## Set a java memory maxsize in GB
 JAVA-MEMORY =

diff --git a/README.md b/README.md
@@ -1,7 +1,7 @@
 # ParlaMint: Comparable Parliamentary Corpora
 
 The [CLARIN ParlaMint project](https://www.clarin.eu/parlamint)
-is compiling comparable parliamentary corpora for a number of countries and languages. 
+compiled comparable parliamentary corpora for a number of countries and languages. 
 
 ParlaMint corpora are interoperable, i.e. encoded to a very constrained common ParlaMint schema, a
 specialisation of the [Parla-CLARIN recommendations](https://clarin-eric.github.io/parla-clarin/),
@@ -20,26 +20,26 @@ translated to English, and is available from the CLARIN.SI repository:
 Publications connected to ParlaMint are available at the
 [ParlaMint project page](https://www.clarin.eu/parlamint#publications-and%C2%A0presentations).
 
-The two most comprehensive publication on ParlaMint corpora are the LREV preprint describing version 4.1
-and the LREV publication describing version 2.1:
+The two most comprehensive publication on ParlaMint corpora are the two open access LREV papers describing
+versions 4.1 and 2.1:
 
 - Tomaž Erjavec, Matyáš Kopp, Nikola Ljubešić, Taja Kuzman, Paul Rayson, Petya Osenova, Maciej
   Ogrodniczuk, Çağrı Çöltekin, Danijel Koržinek, Katja Meden, Jure Skubic, Peter Rupnik, Tommaso
   Agnoloni, José Aires, Starkaður Barkarson, Roberto Bartolini, Núria Bel, Calzada María Pérez,
   Roberts Darģis, Sascha Diwersy, Maria Gavriilidou, van Ruben Heusden, Mikel Iruskieta, Neeme
   Kahusk, Anna Kryvenko, Noémi Ligeti-Nagy, Carmen Magariños, Martin Mölder, Costanza
   Navarretta, Kiril Simov, Lars Magne Tungland, Jouni Tuominen, John Vidler, Adina Ioana Vladu,
-  Tanja Wissik, Väinö Yrjänäinen, Darja Fišer.
-  *ParlaMint II: Advancing Comparable Parliamentary Corpora Across Europe*.
-  (2024).
-  DOI: [10.21203/rs.3.rs-4176128/v1](https://doi.org/10.21203/rs.3.rs-4176128/v1).
+  Tanja Wissik, Väinö Yrjänäinen & Darja Fišer.
+  **ParlaMint II: Advancing Comparable Parliamentary Corpora Across Europe**.
+  *Language Resources & Evaluation* (2024).
+  DOI: [10.1007/s10579-024-09798-w](https://doi.org/10.1007/s10579-024-09798-w).
 
 - Tomaž Erjavec, Maciej Ogrodniczuk, Petya Osenova, Nikola Ljubešić, Kiril Simov, Andrej Pančur,
   Michał Rudolf, Matyáš Kopp, Starkaður Barkarson, Steinþór Steingrímsson, Çağrı Çöltekin, Jesse
   de Does, Katrien Depuydt, Tommaso Agnoloni, Giulia Venturi, María Calzada Pérez, Luciana D. de
   Macedo, Costanza Navarretta, Giancarlo Luxardo, Matthew Coole, Paul Rayson, Vaidas Morkevičius,
   Tomas Krilavičius, Roberts Darǵis, Orsolya Ring, Ruben van Heusden, Maarten Marx & Darja Fišer.
-  The ParlaMint corpora of parliamentary proceedings.
+  **The ParlaMint corpora of parliamentary proceedings**.
   *Language Resources & Evaluation* 57:415–448 (2023).
   DOI: [10.1007/s10579-021-09574-0](https://doi.org/10.1007/s10579-021-09574-0).
 

diff --git a/Scripts/parlamint-add-common-content.xsl b/Scripts/parlamint-add-common-content.xsl
@@ -171,6 +171,10 @@
         <term>Legislature</term>
         <term>Unicameralism</term>
       </xsl:when>
+      <xsl:when test="$country-code = 'IL'">
+        <term>Legislature</term>
+        <term>Unicameralism</term>
+      </xsl:when>
       <xsl:when test="$country-code = 'IS'">
         <term>Legislature</term>
         <term>Unicameralism</term>

diff --git a/Scripts/parlamint-factorize-corpora.pl b/Scripts/parlamint-factorize-corpora.pl
@@ -54,6 +54,7 @@
 $country2lang{'SK'} = 'sk';
 $country2lang{'TR'} = 'tr';
 $country2lang{'UA'} = 'uk, ru';
+$country2lang{'IL'} = 'he';
 
 $bkpName = "BKP";
 $Saxon   = "java -jar $Bin/bin/saxon.jar";

diff --git a/Scripts/parlamint2conllu.pl b/Scripts/parlamint2conllu.pl
@@ -63,6 +63,7 @@ sub usage
 $country2lang{'SK'} = 'sk';
 $country2lang{'TR'} = 'tr';
 $country2lang{'UA'} = 'uk, ru';
+$country2lang{'IL'} = 'he';
 
 print STDERR "INFO: Converting directory $inDir\n";
 my $rootAnaFile = '';