Skip to content

Commit

Permalink
Merge pull request #661 from clarin-eric/data
Browse files Browse the repository at this point in the history 
Data-main
  • Loading branch information
@matyaskopp
matyaskopp authored May 18, 2023
2 parents 819add4 + 4096645 commit 7a473a1
Show file tree
Hide file tree
Showing 1,120 changed files with 1,091,946 additions and 1,242,875 deletions.
488 changes: 257 additions & 231 deletions Data/ParlaMint-AT/ParlaMint-AT-listOrg.xml
View file

Large diffs are not rendered by default.

37,765 changes: 22,096 additions & 15,669 deletions Data/ParlaMint-AT/ParlaMint-AT-listPerson.xml
View file

Large diffs are not rendered by default.

86 changes: 33 additions & 53 deletions Data/ParlaMint-AT/ParlaMint-AT.ana.xml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -56,39 +56,32 @@
</funder>
</titleStmt>
<editionStmt>
<edition>2.1</edition>
<edition>3.0</edition>
</editionStmt>
<extent><!--These numbers do not reflect the size of the sample!-->
<measure unit="speeches" quantity="1234">1234 speeches</measure>
<measure unit="tokens" quantity="1234">1234 words</measure>
<measure unit="words" quantity="1234">1234 words</measure>
<measure unit="speeches" quantity="227991">227,991 speeches</measure>
<measure unit="words" quantity="59916338">59,916,338 words</measure>
</extent>
<publicationStmt>
<publisher>
<orgName xml:lang="de">Die CLARIN Forschungsinfrastruktur</orgName>
<orgName xml:lang="en">The CLARIN research infrastructure</orgName>
<ref target="https://www.clarin.eu/">www.clarin.eu</ref>
</publisher>
<idno subtype="handle" type="URI">http://hdl.handle.net/11356/1432</idno>
<idno type="URI" subtype="handle">http://hdl.handle.net/11356/1488</idno>
<availability status="free">
<licence>http://creativecommons.org/licenses/by/4.0/</licence>
<p xml:lang="de">
Dieses Werk ist lizensiert unter der <ref target="http://creativecommons.org/licenses/by/4.0/">Creative Commons Namensnennung 4.0 International Lizenz (CC BY 4.0)</ref>.
</p>
<p xml:lang="en">
This work is licensed under the <ref target="http://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International License</ref>.
</p>
<p xml:lang="de">Dieses Werk ist lizensiert unter der <ref target="http://creativecommons.org/licenses/by/4.0/">Creative Commons Namensnennung 4.0 International Lizenz (CC BY 4.0)</ref>.</p>
<p xml:lang="en">This work is licensed under the <ref target="http://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International License</ref>.</p>
</availability>
<date when="2022-12-14">2022-12-14</date>
<date when="2023-04-23">2023-04-23</date>
</publicationStmt>
<sourceDesc>
<bibl>
<title type="main" xml:lang="de">Stenographische Protokolle der Plenarsitzungen des Nationalrats der Republik Österreich</title>
<title type="main" xml:lang="en">Shorthand records of the plenary sittings of the National Council of the Austrian parliament</title>
<publisher>
Parlamentsdirektion
</publisher>
<idno type="URI">https://www.parlament.gv.at/PAKT/STPROT</idno>
<publisher>Parlamentsdirektion</publisher>
<idno type="URI" subtype="parliament">https://www.parlament.gv.at/PAKT/STPROT</idno>
<date from="1996-01-15" to="2022-05-19">15.01.1996 - 19.05.2022</date>
</bibl>
</sourceDesc>
Expand All @@ -99,51 +92,40 @@
<ref target="https://www.clarin.eu/content/parlamint">ParlaMint</ref>
</p>
<p xml:lang="en">
<ref target="https://www.clarin.eu/content/parlamint">ParlaMint</ref> is a project that aims to (1) create a multilingual set of comparable corpora of parliamentary proceedings uniformly encoded according to the <ref target="https://github.com/clarin-eric/parla-clarin">Parla-CLARIN recommendations</ref> and covering the COVID-19 pandemic from November 2019 as well as the earlier period from 2015 to serve as a reference corpus; (2) process the corpora linguistically to add Universal Dependencies syntactic structures and Named Entity annotation; (3) make the corpora available through concordancers and Parlameter; and (4) build use cases in Political Sciences and Digital Humanities based on the corpus data.
</p>
<ref target="https://www.clarin.eu/content/parlamint">ParlaMint</ref> is a project that aims to (1) create a multilingual set of comparable corpora of parliamentary proceedings uniformly encoded according to the <ref target="https://clarin-eric.github.io/ParlaMint/">ParlaMint encoding guidelines</ref>, covering the period from 2015 to mid-2022; (2) add linguistic annotations to the corpora and machine-translate them to English; (3) make the corpora available through concordancers; and (4) build use cases in Political Sciences and Digital Humanities based on the corpus data.</p>
</projectDesc>
<editorialDecl>
<correction>
<p>
No correction of source texts was performed.
</p>
<p>No correction of source texts was performed.</p>
</correction>
<normalization>
<p>
Text has not been normalised, except for spacing. Printed matter quoted in the protocols was removed
</p>
<p>Text has not been normalised, except for spacing. Printed matter quoted in the protocols was removed</p>
</normalization>
<hyphenation>
<p>
No end-of-line hyphens were present in the source.
</p>
<p>No end-of-line hyphens were present in the source.</p>
</hyphenation>
<quotation>
<p>
Quotation marks have been left in the text and are not explicitly marked up.
</p>
<p>Quotation marks have been left in the text and are not explicitly marked up.</p>
</quotation>
<segmentation>
<p>
The texts are segmented into utterances (speeches) and segments (corresponding to paragraphs in the source transcription).
</p>
<p>The texts are segmented into utterances (speeches) and segments (corresponding to paragraphs in the source transcription).</p>
</segmentation>
</editorialDecl>
<tagsDecl><!--These numbers do not reflect the size of the sample!-->
<namespace name="http://www.tei-c.org/ns/1.0">
<tagUsage gi="body" occurs="1234"/>
<tagUsage gi="div" occurs="1234"/>
<tagUsage gi="head" occurs="1234"/>
<tagUsage gi="note" occurs="1234"/>
<tagUsage gi="seg" occurs="1234"/>
<tagUsage gi="text" occurs="1234"/>
<tagUsage gi="u" occurs="1234"/>
<tagUsage gi="link" occurs="1234"/>
<tagUsage gi="linkGrp" occurs="1234"/>
<tagUsage gi="name" occurs="1234"/>
<tagUsage gi="pc" occurs="1234"/>
<tagUsage gi="s" occurs="1234"/>
<tagUsage gi="w" occurs="1234"/>
<tagUsage gi="body" occurs="1197"/>
<tagUsage gi="desc" occurs="1197"/>
<tagUsage gi="div" occurs="1197"/>
<tagUsage gi="gap" occurs="1197"/>
<tagUsage gi="incident" occurs="1197"/>
<tagUsage gi="kinesic" occurs="1197"/>
<tagUsage gi="note" occurs="1197"/>
<tagUsage gi="pb" occurs="1197"/>
<tagUsage gi="seg" occurs="1197"/>
<tagUsage gi="text" occurs="1197"/>
<tagUsage gi="time" occurs="1197"/>
<tagUsage gi="u" occurs="1197"/>
<tagUsage gi="vocal" occurs="1197"/>
</namespace>
</tagsDecl>
<classDecl>
Expand All @@ -160,9 +142,7 @@
</classDecl>
<listPrefixDef>
<prefixDef ident="ud-syn" matchPattern="(.+)" replacementPattern="#$1">
<p>
Private URIs with this prefix point to elements giving their name. In this document they are simply local references into the UD-SYN taxonomy categories in the corpus root TEI header.
</p>
<p>Private URIs with this prefix point to elements giving their name. In this document they are simply local references into the UD-SYN taxonomy categories in the corpus root TEI header.</p>
</prefixDef>
</listPrefixDef>
<appInfo>
Expand Down Expand Up @@ -203,14 +183,14 @@
</langUsage>
</profileDesc>
<revisionDesc>
<change when="2022-12-14">
<name>GitHub Action</name>: Made sample.</change>
<change when="2023-04-23">
<name>Tomaž Erjavec</name>: Made sample.</change>
</revisionDesc>
</teiHeader>
<xi:include xmlns:xi="http://www.w3.org/2001/XInclude"
href="ParlaMint-AT_2010-03-24-024-XXIV-NRSITZ-00057.ana.xml"/>
href="ParlaMint-AT_2005-03-31-022-XXII-NRSITZ-00100.ana.xml"/>
<xi:include xmlns:xi="http://www.w3.org/2001/XInclude"
href="ParlaMint-AT_1996-01-15-020-XX-NRSITZ-00001.ana.xml"/>
href="ParlaMint-AT_2014-09-24-025-XXV-NRSITZ-00042.ana.xml"/>
<xi:include xmlns:xi="http://www.w3.org/2001/XInclude"
href="ParlaMint-AT_2022-05-19-027-XXVII-NRSITZ-00159.ana.xml"/>
</teiCorpus>
76 changes: 32 additions & 44 deletions Data/ParlaMint-AT/ParlaMint-AT.xml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -54,39 +54,32 @@
</funder>
</titleStmt>
<editionStmt>
<edition>2.1</edition>
<edition>3.0</edition>
</editionStmt>
<extent><!--These numbers do not reflect the size of the sample!-->
<measure unit="speeches" quantity="1234">1234 speeches</measure>
<measure unit="tokens" quantity="1234">1234 words</measure>
<measure unit="words" quantity="1234">1234 words</measure>
<measure unit="speeches" quantity="227991">227,991 speeches</measure>
<measure unit="words" quantity="59916338">59,916,338 words</measure>
</extent>
<publicationStmt>
<publisher>
<orgName xml:lang="de">Die CLARIN Forschungsinfrastruktur</orgName>
<orgName xml:lang="en">The CLARIN research infrastructure</orgName>
<ref target="https://www.clarin.eu/">www.clarin.eu</ref>
</publisher>
<idno subtype="handle" type="URI">http://hdl.handle.net/11356/1432</idno>
<idno type="URI" subtype="handle">http://hdl.handle.net/11356/1486</idno>
<availability status="free">
<licence>http://creativecommons.org/licenses/by/4.0/</licence>
<p xml:lang="de">
Dieses Werk ist lizensiert unter der <ref target="http://creativecommons.org/licenses/by/4.0/">Creative Commons Namensnennung 4.0 International Lizenz (CC BY 4.0)</ref>.
</p>
<p xml:lang="en">
This work is licensed under the <ref target="http://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International License</ref>.
</p>
<p xml:lang="de">Dieses Werk ist lizensiert unter der <ref target="http://creativecommons.org/licenses/by/4.0/">Creative Commons Namensnennung 4.0 International Lizenz (CC BY 4.0)</ref>.</p>
<p xml:lang="en">This work is licensed under the <ref target="http://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International License</ref>.</p>
</availability>
<date when="2022-12-14">2022-12-14</date>
<date when="2023-04-23">2023-04-23</date>
</publicationStmt>
<sourceDesc>
<bibl>
<title type="main" xml:lang="de">Stenographische Protokolle der Plenarsitzungen des Nationalrats der Republik Österreich</title>
<title type="main" xml:lang="en">Shorthand records of the plenary sittings of the National Council of the Austrian parliament</title>
<publisher>
Parlamentsdirektion
</publisher>
<idno type="URI">https://www.parlament.gv.at/PAKT/STPROT</idno>
<publisher>Parlamentsdirektion</publisher>
<idno type="URI" subtype="parliament">https://www.parlament.gv.at/PAKT/STPROT</idno>
<date from="1996-01-15" to="2022-05-19">15.01.1996 - 19.05.2022</date>
</bibl>
</sourceDesc>
Expand All @@ -97,45 +90,40 @@
<ref target="https://www.clarin.eu/content/parlamint">ParlaMint</ref>
</p>
<p xml:lang="en">
<ref target="https://www.clarin.eu/content/parlamint">ParlaMint</ref> is a project that aims to (1) create a multilingual set of comparable corpora of parliamentary proceedings uniformly encoded according to the <ref target="https://github.com/clarin-eric/parla-clarin">Parla-CLARIN recommendations</ref> and covering the COVID-19 pandemic from November 2019 as well as the earlier period from 2015 to serve as a reference corpus; (2) process the corpora linguistically to add Universal Dependencies syntactic structures and Named Entity annotation; (3) make the corpora available through concordancers and Parlameter; and (4) build use cases in Political Sciences and Digital Humanities based on the corpus data.
</p>
<ref target="https://www.clarin.eu/content/parlamint">ParlaMint</ref> is a project that aims to (1) create a multilingual set of comparable corpora of parliamentary proceedings uniformly encoded according to the <ref target="https://clarin-eric.github.io/ParlaMint/">ParlaMint encoding guidelines</ref>, covering the period from 2015 to mid-2022; (2) add linguistic annotations to the corpora and machine-translate them to English; (3) make the corpora available through concordancers; and (4) build use cases in Political Sciences and Digital Humanities based on the corpus data.</p>
</projectDesc>
<editorialDecl>
<correction>
<p>
No correction of source texts was performed.
</p>
<p>No correction of source texts was performed.</p>
</correction>
<normalization>
<p>
Text has not been normalised, except for spacing. Printed matter quoted in the protocols was removed
</p>
<p>Text has not been normalised, except for spacing. Printed matter quoted in the protocols was removed</p>
</normalization>
<hyphenation>
<p>
No end-of-line hyphens were present in the source.
</p>
<p>No end-of-line hyphens were present in the source.</p>
</hyphenation>
<quotation>
<p>
Quotation marks have been left in the text and are not explicitly marked up.
</p>
<p>Quotation marks have been left in the text and are not explicitly marked up.</p>
</quotation>
<segmentation>
<p>
The texts are segmented into utterances (speeches) and segments (corresponding to paragraphs in the source transcription).
</p>
<p>The texts are segmented into utterances (speeches) and segments (corresponding to paragraphs in the source transcription).</p>
</segmentation>
</editorialDecl>
<tagsDecl><!--These numbers do not reflect the size of the sample!-->
<namespace name="http://www.tei-c.org/ns/1.0">
<tagUsage gi="body" occurs="1234"/>
<tagUsage gi="div" occurs="1234"/>
<tagUsage gi="head" occurs="1234"/>
<tagUsage gi="note" occurs="1234"/>
<tagUsage gi="seg" occurs="1234"/>
<tagUsage gi="text" occurs="1234"/>
<tagUsage gi="u" occurs="1234"/>
<tagUsage gi="body" occurs="1197"/>
<tagUsage gi="desc" occurs="1197"/>
<tagUsage gi="div" occurs="1197"/>
<tagUsage gi="gap" occurs="1197"/>
<tagUsage gi="incident" occurs="1197"/>
<tagUsage gi="kinesic" occurs="1197"/>
<tagUsage gi="note" occurs="1197"/>
<tagUsage gi="pb" occurs="1197"/>
<tagUsage gi="seg" occurs="1197"/>
<tagUsage gi="text" occurs="1197"/>
<tagUsage gi="time" occurs="1197"/>
<tagUsage gi="u" occurs="1197"/>
<tagUsage gi="vocal" occurs="1197"/>
</namespace>
</tagsDecl>
<classDecl>
Expand Down Expand Up @@ -174,14 +162,14 @@
</langUsage>
</profileDesc>
<revisionDesc>
<change when="2022-12-14">
<name>GitHub Action</name>: Made sample.</change>
<change when="2023-04-23">
<name>Tomaž Erjavec</name>: Made sample.</change>
</revisionDesc>
</teiHeader>
<xi:include xmlns:xi="http://www.w3.org/2001/XInclude"
href="ParlaMint-AT_1996-01-15-020-XX-NRSITZ-00001.xml"/>
href="ParlaMint-AT_2005-03-31-022-XXII-NRSITZ-00100.xml"/>
<xi:include xmlns:xi="http://www.w3.org/2001/XInclude"
href="ParlaMint-AT_2010-03-24-024-XXIV-NRSITZ-00057.xml"/>
href="ParlaMint-AT_2014-09-24-025-XXV-NRSITZ-00042.xml"/>
<xi:include xmlns:xi="http://www.w3.org/2001/XInclude"
href="ParlaMint-AT_2022-05-19-027-XXVII-NRSITZ-00159.xml"/>
</teiCorpus>
5 changes: 0 additions & 5 deletions Data/ParlaMint-AT/ParlaMint-AT_1996-01-15-020-XX-NRSITZ-00001-meta.tsv
View file

This file was deleted.

Loading

0 comments on commit 7a473a1

Please sign in to comment.