Update analysis metadata

spraakbanken · Feb 11, 2025 · ec20beb · ec20beb
1 parent 41ce4e1
commit ec20beb
Show file tree

Hide file tree

Showing 13 changed files with 111 additions and 80 deletions.
diff --git a/sparv/modules/geo/metadata.yaml b/sparv/modules/geo/metadata.yaml
@@ -6,7 +6,9 @@ language_codes:
 keywords: []
 standard_reference: ''
 other_references: []
-model: "[GeoNames](https://www.geonames.org/)"
+models:
+  - name: GeoNames
+    url: "https://www.geonames.org/"
 trained_on: ''
 tagset: ''
 evaluation_results: ''

diff --git a/sparv/modules/hunpos/metadata.yaml b/sparv/modules/hunpos/metadata.yaml
@@ -5,11 +5,10 @@ language_codes:
 standard_reference: ''
 other_references:
   - "Hunpos: https://code.google.com/archive/p/hunpos/"
-tool:
-  name: Hunpos
-  url: "https://code.google.com/archive/p/hunpos/"
-licences:
-  tool: BSD-3-Clause
+tools:
+  - name: Hunpos
+    url: "https://code.google.com/archive/p/hunpos/"
+    license: BSD-3-Clause
 trained_on: "[SUC3](https://spraakbanken.gu.se/resurser/suc3)"
 tagset: "[SUC3](https://spraakbanken.gu.se/korp/markup/msdtags.html)"
 evaluation_results: ''
@@ -35,7 +34,9 @@ example_output: |-
   <token pos="NN">korpus</token>
   <token pos="MAD">.</token>
   ```
-model: "[suc3_suc-tags_default-setting_utf8.model](https://github.com/spraakbanken/sparv-models/blob/master/hunpos/suc3_suc-tags_default-setting_utf8.model?raw=true)"
+models:
+  - name: suc3_suc-tags_default-setting_utf8.model
+    url: "https://github.com/spraakbanken/sparv-models/blob/master/hunpos/suc3_suc-tags_default-setting_utf8.model?raw=true"
 description:
   swe: |-
     Meningssegment analyseras och annoteras med ordklasstaggar. Ingår inte längre i
@@ -67,7 +68,9 @@ example_output: |-
   <token msd="NN.UTR.SIN.IND.NOM">korpus</token>
   <token msd="MAD">.</token>
   ```
-model: "[suc3_suc-tags_default-setting_utf8.model](https://github.com/spraakbanken/sparv-models/blob/master/hunpos/suc3_suc-tags_default-setting_utf8.model?raw=true)"
+models:
+  - name: suc3_suc-tags_default-setting_utf8.model
+    url: "https://github.com/spraakbanken/sparv-models/blob/master/hunpos/suc3_suc-tags_default-setting_utf8.model?raw=true"
 description:
   swe: |-
     Meningssegment analyseras och annoteras med ordklasstaggar och morfosyntaktisk information. Ingår inte längre i
@@ -113,18 +116,21 @@ example_extra: |-
     language: swe
     variety: "1800"
   ```
-model: |-
-  - [suc3_suc-tags_default-setting_utf8.model](https://github.com/spraakbanken/sparv-models/blob/master/hunpos/suc3_suc-tags_default-setting_utf8.model?raw=true)
-  - a word list along with the words' morphosyntactic information generated from the [Dalin
-  morphology](https://spraakbanken.gu.se/resurser/dalinm) and the [Swedberg
-  morphology](https://spraakbanken.gu.se/resurser/swedbergm)
+models:
+  - name: suc3_suc-tags_default-setting_utf8.model
+    url: "https://github.com/spraakbanken/sparv-models/blob/master/hunpos/suc3_suc-tags_default-setting_utf8.model?raw=true"
+  - name: dalinm-swedberg_saldo_suc-tags.morphtable
+    description: |-
+      A word list along with the words' morphosyntactic information generated from the [Dalin
+      morphology](https://spraakbanken.gu.se/resurser/dalinm) and the [Swedberg
+      morphology](https://spraakbanken.gu.se/resurser/swedbergm)
 description:
   swe: |-
     Meningssegment analyseras och annoteras med ordklasstaggar. Utöver ordklasstaggningsmodellen använder Hunpos listor
     med böjningsformer för att kunna generera bättre ordklasstaggar för 1800-talssvenska.
   eng: |-
     Sentence segments are analysed to enrich tokens with part-of-speech tags. In addition to the pos model inflection
-    lists are provided to Hunpos to make more accuare part-of-speech predictions for Swedish from the 1800's.
+    lists are provided to Hunpos to make more accurate part-of-speech predictions for Swedish from the 1800's.
 created: 2012-10-23
 updated: 2015-09-11
 ---
@@ -163,19 +169,22 @@ example_extra: |-
     language: swe
     variety: "1800"
   ```
-model: |-
-  - [suc3_suc-tags_default-setting_utf8.model](https://github.com/spraakbanken/sparv-models/blob/master/hunpos/suc3_suc-tags_default-setting_utf8.model?raw=true)
-  - a word list along with the words' morphosyntactic information generated from the [Dalin
-  morphology](https://spraakbanken.gu.se/resurser/dalinm) and the [Swedberg
-  morphology](https://spraakbanken.gu.se/resurser/swedbergm)
+models:
+  - name: suc3_suc-tags_default-setting_utf8.model
+    url: "https://github.com/spraakbanken/sparv-models/blob/master/hunpos/suc3_suc-tags_default-setting_utf8.model?raw=true"
+  - name: dalinm-swedberg_saldo_suc-tags.morphtable
+    description: |-
+      A word list along with the words' morphosyntactic information generated from the [Dalin
+      morphology](https://spraakbanken.gu.se/resurser/dalinm) and the [Swedberg
+      morphology](https://spraakbanken.gu.se/resurser/swedbergm)
 description:
   swe: |-
     Meningssegment analyseras och annoteras med ordklasstaggar och morfosyntaktisk information. Utöver
     ordklasstaggningsmodellen använder Hunpos listor med böjningsformer för att kunna generera bättre ordklasstaggar för
     1800-talssvenska.
   eng: |-
     Sentence segments are analysed to enrich tokens with part-of-speech tags and morphosyntactic information. In
-    addition to the pos model inflection lists are provided to Hunpos to make more accuare part-of-speech predictions
+    addition to the pos model inflection lists are provided to Hunpos to make more accurate part-of-speech predictions
     for Swedish from the 1800's.
 created: 2012-10-23
 updated: 2015-09-11
diff --git a/sparv/modules/lexical_classes/metadata.yaml b/sparv/modules/lexical_classes/metadata.yaml
@@ -18,7 +18,9 @@ standard_reference: "[Lars Borin, Luis Nieto Piña, Richard Johansson (2015): He
 other_references:
   - "[Lars Borin, Jens Allwood, Gerard de Melo (2014): Bring vs. MTRoget: Evaluating automatic thesaurus translation, in Proceedings of LREC 2014, May 26-31, 2014 Reykjavik, Iceland](https://gup.ub.gu.se/publication/198549)"
 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)"
+models:
+  - name: Blingbring frequency model
+    url: "https://github.com/spraakbanken/sparv-models/blob/master/lexical_classes/blingbring.freq.gp2008%2Bsuc3%2Bromi.pickle"
 ---
 id: sbx-swe-lexical_classes_token-sparv-blingbring
 parent: blingbring-parent
@@ -145,7 +147,9 @@ standard_reference: "[Dana Dannélls, Lars Borin, Karin Friberg Heppin (2021): T
 other_references:
   - "Dana Dannélls, Lars Borin, Karin Friberg Heppin (2021): The Swedish FrameNet++ Harmonization, integration, method development and practical language technology applications. John Benjamins: Amsterdam, Philadelphia. ISBN 978 90 272 5848 9."
 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)"
+models:
+  - name: Frequency model
+    url: "https://github.com/spraakbanken/sparv-models/blob/master/lexical_classes/swefn.freq.gp2008%2Bsuc3%2Bromi.pickle"
 ---
 id: sbx-swe-lexical_classes_token-sparv-swefn
 parent: swefn-parent

diff --git a/sparv/modules/malt/metadata.yaml b/sparv/modules/malt/metadata.yaml
@@ -35,10 +35,12 @@ standard_reference: |-
 other_references:
   - "Maltparser: https://www.maltparser.org/download.html"
   - 'https://aclanthology.org/2021.nodalida-main.20/'
-tool:
-  name: Maltparser
-  url: "https://www.maltparser.org/"
-model: "[Swemalt](https://www.maltparser.org/mco/swedish_parser/swemalt.html)"
+tools:
+  - name: Maltparser
+    url: "https://www.maltparser.org/"
+models:
+  - name: Swemalt
+    url: "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)"
 evaluation_results: Labelled Attachment Score 0.78 (using the TalbankenSBX train-dev-test split)

diff --git a/sparv/modules/phrase_structure/metadata.yaml b/sparv/modules/phrase_structure/metadata.yaml
@@ -45,7 +45,6 @@ example_output: |-
   ```
 standard_reference: ''
 other_references: []
-model: "Method has no model"
 trained_on: "[TalbankenSBX](https://spraakbanken.gu.se/resurser/talbanken)"
 tagset: "See description below"
 evaluation_results: ''

diff --git a/sparv/modules/readability/metadata.yaml b/sparv/modules/readability/metadata.yaml
@@ -5,7 +5,6 @@ language_codes:
   - swe
 keywords: []
 other_references: []
-model: ''
 trained_on: ''
 tagset: ''
 evaluation_results: ''

diff --git a/sparv/modules/saldo/metadata.yaml b/sparv/modules/saldo/metadata.yaml
@@ -4,7 +4,9 @@ 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: []
-model: "[SALDO's morphology](https://spraakbanken.gu.se/resurser/saldom)"
+models:
+  - name: SALDO's morphology
+    url: "https://spraakbanken.gu.se/resurser/saldom"
 trained_on: ''
 tagset: ''
 evaluation_results: ''

diff --git a/sparv/modules/segment/metadata.yaml b/sparv/modules/segment/metadata.yaml
@@ -1,13 +1,11 @@
-
 id: segment-nltk-parent
 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:
-  name: NLTK
-  url: "https://www.nltk.org/"
-model: ''
+tools:
+  - name: NLTK
+    url: "https://www.nltk.org/"
 trained_on: ''
 tagset: ''
 evaluation_results: ''
@@ -351,9 +349,10 @@ example_output: |-
   <token>.</token>
   ```
 standard_reference: ''
-model: |-
-  - [bettertokenizer.sv](https://raw.githubusercontent.com/spraakbanken/sparv-models/master/segment/bettertokenizer.sv)
-  - bettertokenizer.sv.saldo-tokens
+models:
+  - name: bettertokenizer.sv
+    url: "https://raw.githubusercontent.com/spraakbanken/sparv-models/master/segment/bettertokenizer.sv"
+  - name: bettertokenizer.sv.saldo-tokens
 trained_on: "[SALDOs morphology](https://spraakbanken.gu.se/resurser/saldom)"
 description:
   swe: |-
@@ -399,7 +398,9 @@ example_output: |-
     <token>.</token>
   </sentence>
   ```
-model: "[punkt-nltk-svenska.pickle](https://github.com/spraakbanken/sparv-models/blob/master/segment/punkt-nltk-svenska.pickle?raw=true)"
+models:
+  - name: punkt-nltk-svenska.pickle
+    url: "https://github.com/spraakbanken/sparv-models/blob/master/segment/punkt-nltk-svenska.pickle?raw=true"
 trained_on: "[StorSUC](https://spraakbanken.gu.se/resurser/storsuc)"
 description:
   swe: |-

diff --git a/sparv/modules/sensaldo/metadata.yaml b/sparv/modules/sensaldo/metadata.yaml
@@ -49,7 +49,9 @@ 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
-model: "[Sensaldo](https://spraakbanken.gu.se/resurser/sensaldo)"
+models:
+  - name: Sensaldo
+    url: "https://spraakbanken.gu.se/resurser/sensaldo"
 trained_on: ''
 tagset: ''
 evaluation_results: ''