Update analysis metadata

spraakbanken · Jan 20, 2025 · ad1ad4f · ad1ad4f
1 parent 078e326
commit ad1ad4f
Show file tree

Hide file tree

Showing 14 changed files with 79 additions and 67 deletions.
diff --git a/sparv/modules/conll_export/metadata.yaml b/sparv/modules/conll_export/metadata.yaml
@@ -1,4 +1,4 @@
-id: export-conllu
+id: sbx-swe-export-conllu
 name:
   swe: CoNLL-U-export
   eng: CoNLL-U export

diff --git a/sparv/modules/geo/metadata.yaml b/sparv/modules/geo/metadata.yaml
@@ -6,15 +6,14 @@ language_codes:
 keywords: []
 standard_reference: ''
 other_references: []
-tool: ''
 model: "[GeoNames](https://www.geonames.org/)"
 trained_on: ''
 tagset: ''
 evaluation_results: ''
 created: 2018-05-28
 updated: 2022-05-18
 ---
-id: swe-geotagcontext-sparv
+id: sbx-swe-geotagcontext-sparv
 parent: geo-parent
 name:
   swe: Geotaggning av platsnamn från kontext
@@ -67,7 +66,7 @@ description:
     the [GeoNames database](https://www.geonames.org/). This annotation can be applied to any text chunk, e.g. texts,
     paragraphs, sentences or tokens.
 ---
-id: swe-geotagmetadata-sparv
+id: sbx-swe-geotagmetadata-sparv
 parent: geo-parent
 name:
   swe: Geotagging av platsnamn från metadata

diff --git a/sparv/modules/hunpos/metadata.yaml b/sparv/modules/hunpos/metadata.yaml
@@ -5,12 +5,16 @@ language_codes:
 standard_reference: ''
 other_references:
   - "Hunpos: https://code.google.com/archive/p/hunpos/"
-tool: "Hunpos"
+tool:
+  name: Hunpos
+  url: "https://code.google.com/archive/p/hunpos/"
+licences:
+  tool: BSD-3-Clause
 trained_on: "[SUC3](https://spraakbanken.gu.se/resurser/suc3)"
 tagset: "[SUC3](https://spraakbanken.gu.se/korp/markup/msdtags.html)"
 evaluation_results: ''
 ---
-id: swe-pos-hunpos-suc3
+id: sbx-swe-pos-hunpos-suc3
 parent: hunpos-parent
 name:
   swe: SUC-ordklasstaggning med Hunpos
@@ -42,7 +46,7 @@ description:
 created: 2010-12-15
 updated: 2018-05-28
 ---
-id: swe-msd-hunpos-suc3
+id: sbx-swe-msd-hunpos-suc3
 parent: hunpos-parent
 name:
   swe: Morfosyntaktisk SUC-taggning med Hunpos
@@ -74,7 +78,7 @@ description:
 created: 2010-12-15
 updated: 2018-05-28
 ---
-id: swe-pos-hunpos-suc3-1800
+id: sbx-swe-pos-hunpos-suc3-1800
 parent: hunpos-parent
 name:
   swe: SUC-ordklasstaggning med Hunpos för 1800-talssvenska
@@ -124,7 +128,7 @@ description:
 created: 2012-10-23
 updated: 2015-09-11
 ---
-id: swe-msd-hunpos-suc3-1800
+id: sbx-swe-msd-hunpos-suc3-1800
 parent: hunpos-parent
 name:
   swe: Morfosyntaktisk SUC-taggning med Hunpos för 1800-talssvenska

diff --git a/sparv/modules/lexical_classes/metadata.yaml b/sparv/modules/lexical_classes/metadata.yaml
@@ -4,7 +4,6 @@ language_codes:
   - swe
 keywords: []
 abstract: true
-tool: ''
 trained_on: |-
     Reference corpora for relative frequencies: [Göteborgsposten 2008](https://spraakbanken.gu.se/resurser/gp2008), [SUC
     3.0](https://spraakbanken.gu.se/resurser/suc3), [Bonniersromaner I
@@ -21,7 +20,7 @@ other_references:
 tagset: "[Blingbring](https://spraakbanken.gu.se/resurser/blingbring)"
 model: "[Blingbring frequency model](https://github.com/spraakbanken/sparv-models/blob/master/lexical_classes/blingbring.freq.gp2008%2Bsuc3%2Bromi.pickle)"
 ---
-id: swe-lexical_classes_token-sparv-blingbring
+id: sbx-swe-lexical_classes_token-sparv-blingbring
 parent: blingbring-parent
 name:
   swe: Lexikala klasser från Blingbring, tokennivå
@@ -65,7 +64,7 @@ description:
     versions of Blingbring.
 created: 2017-09-05
 ---
-id: swe-lexical_classes_text-sparv-blingbring
+id: sbx-swe-lexical_classes_text-sparv-blingbring
 parent: blingbring-parent
 name:
   swe: Lexikala klasser från Blingbring, textnivå
@@ -148,7 +147,7 @@ other_references:
 tagset: "[Swedish FrameNet (SweFN)](https://spraakbanken.gu.se/resurser/swefn)"
 model: "[Frequency model](https://github.com/spraakbanken/sparv-models/blob/master/lexical_classes/swefn.freq.gp2008%2Bsuc3%2Bromi.pickle)"
 ---
-id: swe-lexical_classes_token-sparv-swefn
+id: sbx-swe-lexical_classes_token-sparv-swefn
 parent: swefn-parent
 name:
   swe: Lexikala klasser från SweFN, tokennivå
@@ -186,7 +185,7 @@ description:
     classes.
 created: 2017-09-21
 ---
-id: swe-lexical_classes_text-sparv-swefn
+id: sbx-swe-lexical_classes_text-sparv-swefn
 parent: swefn-parent
 name:
   swe: Lexikala klasser från SweFN, textnivå

diff --git a/sparv/modules/malt/metadata.yaml b/sparv/modules/malt/metadata.yaml
@@ -1,4 +1,4 @@
-id: swe-dependency-malt-treebank
+id: sbx-swe-dependency-malt-treebank
 name:
   swe: Dependensparsning med MaltParser
   eng: Dependency parsing with MaltParser
@@ -35,7 +35,9 @@ standard_reference: |-
 other_references:
   - "Maltparser: https://www.maltparser.org/download.html"
   - 'https://aclanthology.org/2021.nodalida-main.20/'
-tool: "Maltparser"
+tool:
+  name: Maltparser
+  url: "https://www.maltparser.org/"
 model: "[Swemalt](https://www.maltparser.org/mco/swedish_parser/swemalt.html)"
 trained_on: "[Svensk trädbank (the TalbankenSTB part)](https://spraakbanken.gu.se/resurser/sv-treebank)"
 tagset: "[MambaDep](https://svn.spraakdata.gu.se/sb-arkiv/pub/mamba.html)"

diff --git a/sparv/modules/phrase_structure/metadata.yaml b/sparv/modules/phrase_structure/metadata.yaml
@@ -1,4 +1,4 @@
-id: swe-phrasestructure-sparv
+id: sbx-swe-phrasestructure-sparv
 name:
   swe: Svensk frasstrukturparsning
   eng: Swedish phrase structure parsing
@@ -45,7 +45,6 @@ example_output: |-
   ```
 standard_reference: ''
 other_references: []
-tool: ''
 model: "Method has no model"
 trained_on: "[TalbankenSBX](https://spraakbanken.gu.se/resurser/talbanken)"
 tagset: "See description below"

diff --git a/sparv/modules/readability/metadata.yaml b/sparv/modules/readability/metadata.yaml
@@ -5,15 +5,14 @@ language_codes:
   - swe
 keywords: []
 other_references: []
-tool: ''
 model: ''
 trained_on: ''
 tagset: ''
 evaluation_results: ''
 created: 2018-03-28
 updated: 2018-03-28
 ---
-id: swe-readability-sparv-lix
+id: sbx-swe-readability-sparv-lix
 parent: readability-parent
 name:
   swe: Annotering av läsbarhetsindex (LIX) för texter
@@ -76,7 +75,7 @@ description:
     average word count per sentence and ratio of long words (exceeding six letters). The value is calculated as O / M +
     L x 100 / O, where O = word count, M = sentence count and L = long word count.
 ---
-id: swe-readability-sparv-nk
+id: sbx-swe-readability-sparv-nk
 parent: readability-parent
 name:
   swe: Annotering av Nominalkvot (NK) för texter
@@ -137,7 +136,7 @@ description:
     dividing this by the number of verbs, adverbs and pronouns. A high nominal ratio suggests a high density of
     information, which can also mean that the text is difficult to read.
 ---
-id: swe-readability-sparv-ovix
+id: sbx-swe-readability-sparv-ovix
 parent: readability-parent
 name:
   swe: Annotering av Ordvariationsindex (OVIX) för texter

diff --git a/sparv/modules/saldo/metadata.yaml b/sparv/modules/saldo/metadata.yaml
@@ -4,13 +4,12 @@ language_codes:
   - swe
 standard_reference: "[Borin/Forsberg/Lönngren 2013: SALDO: a touch of yin to WordNet's yang](http://dx.doi.org/10.1007/s10579-013-9233-4)"
 other_references: []
-tool: "Sparv"
 model: "[SALDO's morphology](https://spraakbanken.gu.se/resurser/saldom)"
 trained_on: ''
 tagset: ''
 evaluation_results: ''
 ---
-id: swe-lemmatization-sparv-saldo
+id: sbx-swe-lemmatization-sparv-saldo
 parent: saldo-parent
 name:
   swe: Annotering av SALDO-grundformer
@@ -44,7 +43,7 @@ description:
 created: 2010-12-15
 updated: 2018-03-28
 ---
-id: swe-lemgram-sparv-saldo
+id: sbx-swe-lemgram-sparv-saldo
 parent: saldo-parent
 name:
   swe: Annotering av SALDO-lemgram
@@ -77,7 +76,7 @@ description:
 created: 2010-12-15
 updated: 2018-03-28
 ---
-id: swe-sense-sparv-saldo
+id: sbx-swe-sense-sparv-saldo
 parent: saldo-parent
 name:
   swe: Annotering av SALDO-identifierare
@@ -107,7 +106,7 @@ description:
 created: 2010-12-15
 updated: 2018-03-28
 ---
-id: swe-compound-sparv-saldolemgram
+id: sbx-swe-compound-sparv-saldolemgram
 parent: saldo-parent
 name:
   swe: Sammansättningsanalys med hjälp av SALDO-lemgram
@@ -148,7 +147,7 @@ description:
 created: 2018-03-28
 updated: 2020-07-09
 ---
-id: swe-compound-sparv-saldowords
+id: sbx-swe-compound-sparv-saldowords
 parent: saldo-parent
 name:
   swe: Sammansättningsanalys med hjälp av SALDO-ordformer
@@ -189,7 +188,7 @@ description:
 created: 2018-03-28
 updated: 2020-07-09
 ---
-id: swe-lemmatization-sparv-saldo2
+id: sbx-swe-lemmatization-sparv-saldo2
 parent: saldo-parent
 name:
   swe: Annotering av SALDO-grundformer (utökade)

diff --git a/sparv/modules/segment/metadata.yaml b/sparv/modules/segment/metadata.yaml
@@ -4,7 +4,9 @@ abstract: true
 keywords: []
 standard_reference: "Bird, Steven, Edward Loper and Ewan Klein (2009), Natural Language Processing with Python. O’Reilly Media Inc."
 other_references: []
-tool: "NLTK"
+tool:
+  name: NLTK
+  url: "https://www.nltk.org/"
 model: ''
 trained_on: ''
 tagset: ''
@@ -17,7 +19,7 @@ description:
 created: 2010-12-15
 updated: 2021-05-07
 ---
-id: tokenization-sparv-linebreaks
+id: sbx-mul-tokenization-sparv-linebreaks
 parent: segment-nltk-parent
 name:
   swe: Radbrytningstokenisering
@@ -44,7 +46,7 @@ example_extra: |-
     token_segmenter: linebreaks
   ```
 ---
-id: sentence-sparv-linebreaks
+id: sbx-mul-sentence-sparv-linebreaks
 parent: segment-nltk-parent
 name:
   swe: Radbrytningssegmentering, meningar
@@ -80,7 +82,7 @@ example_extra: |-
     sentence_segmenter: linebreaks
   ```
 ---
-id: paragraph-sparv-linebreaks
+id: sbx-mul-paragraph-sparv-linebreaks
 parent: segment-nltk-parent
 name:
   swe: Radbrytningssegmentering, stycken
@@ -120,7 +122,7 @@ example_extra: |-
     paragraph_segmenter: linebreaks
   ```
 ---
-id: tokenization-sparv-blanklines
+id: sbx-mul-tokenization-sparv-blanklines
 parent: segment-nltk-parent
 name:
   swe: Tomradstokenisering
@@ -147,7 +149,7 @@ example_extra: |-
     token_segmenter: blanklines
   ```
 ---
-id: sentence-sparv-blanklines
+id: sbx-mul-sentence-sparv-blanklines
 parent: segment-nltk-parent
 name:
   swe: Tomradssegmentering, meningar
@@ -183,7 +185,7 @@ example_extra: |-
     sentence_segmenter: blanklines
   ```
 ---
-id: paragraph-sparv-blanklines
+id: sbx-mul-paragraph-sparv-blanklines
 parent: segment-nltk-parent
 name:
   swe: Tomradssegmentering, stycken
@@ -223,7 +225,7 @@ example_extra: |-
     paragraph_segmenter: blanklines
   ```
 ---
-id: tokenization-sparv-whitespace
+id: sbx-mul-tokenization-sparv-whitespace
 parent: segment-nltk-parent
 name:
   swe: Blankteckentokenisering
@@ -250,7 +252,7 @@ example_extra: |-
     token_segmenter: whitespace
   ```
 ---
-id: sentence-sparv-whitespace
+id: sbx-mul-sentence-sparv-whitespace
 parent: segment-nltk-parent
 name:
   swe: Blankteckensegmentering, meningar
@@ -286,7 +288,7 @@ example_extra: |-
     sentence_segmenter: whitespace
   ```
 ---
-id: paragraph-sparv-whitespace
+id: sbx-mul-paragraph-sparv-whitespace
 parent: segment-nltk-parent
 name:
   swe: Blankteckensegmentering, stycken
@@ -326,7 +328,7 @@ example_extra: |-
     paragraph_segmenter: whitespace
   ```
 ---
-id: swe-tokenization-sparv-betterword
+id: sbx-swe-tokenization-sparv-betterword
 parent: segment-nltk-parent
 name:
   swe: Svensk tokenisering
@@ -366,7 +368,7 @@ description:
     tokenizer for other languages.
 updated: 2021-05-07
 ---
-id: swe-sentence-punkt-storsuc
+id: sbx-swe-sentence-punkt-storsuc
 parent: segment-nltk-parent
 name:
   swe: Svensk meningssegmentering
@@ -413,7 +415,7 @@ description:
     is, however, possible to configure the sentence segmenter for other languages.
 updated: 2021-09-02
 ---
-id: sentence-punkt
+id: sbx-mul-sentence-punctuation
 parent: segment-nltk-parent
 name:
   swe: Meningssegmentering utifrån skiljetecken

diff --git a/sparv/modules/sensaldo/metadata.yaml b/sparv/modules/sensaldo/metadata.yaml
@@ -1,4 +1,4 @@
-id: swe-sentiment-sparv-sensaldo
+id: sbx-swe-sentiment-sparv-sensaldo
 name:
   swe: Sentimentanalys per token med SenSALDO
   eng: Sentiment analysis per token using SenSALDO
@@ -49,7 +49,6 @@ standard_reference: 'http://www.lrec-conf.org/proceedings/lrec2018/summaries/857
 other_references:
   - http://www.lrec-conf.org/proceedings/lrec2018/summaries/846.html
   - https://gup.ub.gu.se/publication/264721?lang=sv
-tool: ''
 model: "[Sensaldo](https://spraakbanken.gu.se/resurser/sensaldo)"
 trained_on: ''
 tagset: ''