more metadata

spraakbanken · Nov 4, 2024 · 4959865 · 4959865
1 parent c5dcff0
commit 4959865
Show file tree

Hide file tree

Showing 5 changed files with 317 additions and 0 deletions.
diff --git a/sparv/modules/conll_export/metadata.yaml b/sparv/modules/conll_export/metadata.yaml
@@ -0,0 +1,26 @@
+id: export-conllu
+name:
+  swe: CoNLL-U-export
+  eng: CoNLL-U export
+short_description:
+  swe: Export av korpusdata i Språkbanken Texts CoNLL-U-format
+  eng: Export of corpus data in Språkbanken Text's CoNLL-U format
+task: export
+keywords:
+ - conll-u
+ - export
+sparv_handler: conll_export:conllu
+example_output: |-
+  ```
+  # global.columns = ID FORM LEMMA UPOS XPOS FEATS HEAD DEPREL DEPS MISC
+  # document_name = rävar
+  # text_date = 2017-01-10
+  # text_title = Rödräv
+  # sent_id = 157
+  1	Rödräven	rödräv	NN	NN.UTR.SIN.DEF.NOM	Case=Nom|Definite=Def|Gender=Com|Number=Sing	2	ss	_	_
+  2	är	vara	VB	VB.PRS.AKT	Mood=Ind|Tense=Pres|VerbForm=Fin|Voice=Act	0	root	_	_
+  3	ett	en	DT	DT.NEU.SIN.IND	Definite=Ind|Gender=Neut|Number=Sing	4	dt	_	_
+  4	hunddjur	hunddjur	NN	NN.NEU.SIN.IND.NOM	Case=Nom|Definite=Ind|Gender=Neut|Number=Sing	2	sp	_	_
+  ```
+created: 2020-11-20
+updated: 2022-03-25
diff --git a/sparv/modules/malt/metadata.yaml b/sparv/modules/malt/metadata.yaml
@@ -0,0 +1,50 @@
+id: swe-dependency-malt-treebank
+name:
+  swe: Dependensparsning med MaltParser
+  eng: Dependency parsing with MaltParser
+short_description:
+  swe: Svensk dependensparsning tränad på Svensk trädbank baserad på MaltParser
+  eng: Swedish dependency parsing from MaltParser trained on Sweedish treebank
+task: dependency parsing
+language_codes:
+  - swe
+keywords:
+  - dependency parsing
+annotations:
+  - <token>:malt.ref
+  - <token>:malt.dephead_ref
+  - <token>:malt.deprel
+example_output: |-
+  ```xml
+  <token dephead_ref="4" deprel="SS" ref="1">Alfred</token>
+  <token dephead_ref="1" deprel="HD" ref="2">Bernhard</token>
+  <token dephead_ref="1" deprel="HD" ref="3">Nobel</token>
+  <token deprel="ROOT" ref="4">var</token>
+  <token dephead_ref="8" deprel="DT" ref="5">en</token>
+  <token dephead_ref="8" deprel="AT" ref="6">svensk</token>
+  <token dephead_ref="8" deprel="CJ" ref="7">kemist</token>
+  <token dephead_ref="9" deprel="DT" ref="8">och</token>
+  <token dephead_ref="4" deprel="SP" ref="9">stiftare</token>
+  <token dephead_ref="9" deprel="ET" ref="10">av</token>
+  <token dephead_ref="10" deprel="PA" ref="11">Nobelpriset</token>
+  <token dephead_ref="4" deprel="IP" ref="12">.</token>
+  ```
+standard_reference: |-
+    Joakim Nivre, Johan Hall, and Jens Nilsson. 2006. MaltParser: A Data-Driven Parser-Generator for Dependency Parsing.
+    In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy.
+    European Language Resources Association (ELRA).
+other_references:
+  - "Maltparser: https://www.maltparser.org/download.html"
+  - 'https://aclanthology.org/2021.nodalida-main.20/'
+tool: "Maltparser"
+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)"
+evaluation_results: Labelled Attachment Score 0.78 (using the TalbankenSBX train-dev-test split)
+description:
+  swe: |-
+    Denna Maltparser model har konfigurerats för svenska och tränats på TalbankenSTB-korpusen.
+  eng: |-
+    This MaltParser model configured for Swedish has been trained on the TalbankenSTB corpus.
+created: 2010-12-15
+updated: 2021-06-01
diff --git a/sparv/modules/phrase_structure/metadata.yaml b/sparv/modules/phrase_structure/metadata.yaml
@@ -0,0 +1,97 @@
+id: swe-phrasestructure-sparv
+name:
+  swe: Svensk frasstrukturparsning
+  eng: Swedish phrase structure parsing
+short_description:
+  swe: Svensk frastrukturparser konverterade från Mamba-Dep dependensanalys
+  eng: Swedish phrase structure parser converted from Mamba-Dep dependency analysis
+task: phrase structure parsing
+language_codes:
+  - swe
+keywords:
+  - phrase structure parsing
+annotations:
+  - phrase_structure.phrase
+  - phrase_structure.phrase:phrase_structure.name
+  - phrase_structure.phrase:phrase_structure.func
+example_output: |-
+  ```xml
+  <phrase func="ROOT" name="S">
+    <phrase func="SS" name="NP">
+      <token>Alfred</token>
+      <token>Bernhard</token>
+      <token>Nobel</token>
+    </phrase>
+    <token>var</token>
+    <phrase func="SP" name="NP">
+      <phrase func="DT" name="NP">
+        <token>en</token>
+        <phrase func="AT" name="ADJP">
+          <token>svensk</token>
+          <phrase func="CJ" name="NP">
+            <token>kemist</token>
+          </phrase>
+        </phrase>
+        <token>och</token>
+      </phrase>
+      <token>stiftare</token>
+      <phrase func="ET" name="PrP">
+        <token>av</token>
+        <phrase func="PA" name="NP">
+          <token>Nobelpriset</token>
+          <token>.</token>
+        </phrase>
+      </phrase>
+    </phrase>
+  </phrase>
+  ```
+standard_reference: ''
+other_references: []
+tool: ''
+model: "Method has no model"
+trained_on: "[TalbankenSBX](https://spraakbanken.gu.se/resurser/talbanken)"
+tagset: "See description below"
+evaluation_results: ''
+description:
+  swe: |-
+    Konverterar svenska frasstrukturer från Mamba-Dep dependensanalys med hjälp av en regel-baserad heuristik. Nedan är
+    fulla listan av möjliga frastrukturer:
+
+    NP: noun phrase  
+    NP-wh: noun phrase with a relativizer, e.g. "whose mother"  
+    PrP: prepositional phrase  
+    PrP-wh: prepositional phrase with a relativizer, t.e. "in which"  
+    SBAR: subordinate clause introduced by a subordinator  
+    S: clause  
+    S-wh: clause introduced by a relativizer  
+    S-imp: clause in the imperative  
+    VP-sup: verb phrase using the supine  
+    VP-att: verb phrase with the infinitive, including the infinitive marker "att"  
+    VP-inf: verb phrase with the infinitive, without an infinitive marker  
+    VP-fin: finite verb phrase  
+    ADJP: adjective phrase  
+    ADVP: adverb phrase  
+    ADVP-wh: adverb phrase with a relativizer  
+    QP: numeral phrase
+  eng: |-
+    Converts swedish phrase structures from Mamba-Dep dependency analysis using a rule-based heuristic. Below is the
+    complete list of possible phrase structure labels:
+
+    NP: noun phrase  
+    NP-wh: noun phrase with a relativizer, e.g. "whose mother"  
+    PrP: prepositional phrase  
+    PrP-wh: prepositional phrase with a relativizer, t.e. "in which"  
+    SBAR: subordinate clause introduced by a subordinator  
+    S: clause  
+    S-wh: clause introduced by a relativizer  
+    S-imp: clause in the imperative  
+    VP-sup: verb phrase using the supine  
+    VP-att: verb phrase with the infinitive, including the infinitive marker "att"  
+    VP-inf: verb phrase with the infinitive, without an infinitive marker  
+    VP-fin: finite verb phrase  
+    ADJP: adjective phrase  
+    ADVP: adverb phrase  
+    ADVP-wh: adverb phrase with a relativizer  
+    QP: numeral phrase
+created: 2018-03-28
+updated: 2018-03-28
diff --git a/sparv/modules/swener/metadata.yaml b/sparv/modules/swener/metadata.yaml
@@ -0,0 +1,83 @@
+id: swe-namedentity-swener
+name:
+  swe: Namnigenkänning med HFST-SweNER
+  eng: Named entity recognition with HFST-SweNER
+short_description:
+  swe: Namnigenkänning känner igen och förser namn och namnliknande uttryck (s.k. entiteter) i löpande text med fördefinierade etiketter, som organisation, person eller plats.
+  eng: Named entity recognition (NER) recognises named entities such as locations, persons and time expressions in text.
+task: named entity recognition
+language_codes:
+  - swe
+keywords:
+  - ner
+annotations:
+  - swener.ne
+  - swener.ne:swener.name
+  - swener.ne:swener.ex
+  - swener.ne:swener.type
+  - swener.ne:swener.subtype
+example_output: |-
+  ```xml
+  <ne ex="ENAMEX" name="Alfred Bernhard Nobel" subtype="HUM" type="PRS">
+    <token>Alfred</token>
+    <token>Bernhard</token>
+    <token>Nobel</token>
+  </ne>
+  <token>,</token>
+  <token>född</token>
+  <ne ex="TIMEX" name="21 oktober 1833" subtype="DAT" type="TME">
+    <token>21</token>
+    <token>oktober</token>
+    <token>1833</token>
+  </ne>
+  <token>i</token>
+  <ne ex="ENAMEX" name="Stockholm" subtype="PPL" type="LOC">
+    <token>Stockholm</token>
+  </ne>
+  <token>,</token>
+  <ne ex="ENAMEX" name="Italien" subtype="PPL" type="LOC">
+    <token>Italien</token>
+  </ne>
+  <token>,</token>
+  <token>var</token>
+  <token>en</token>
+  <token>svensk</token>
+  <token>kemist</token>
+  <token>och</token>
+  <token>stiftare</token>
+  <token>av</token>
+  <ne ex="ENAMEX" name="Nobelpriset" subtype="PRZ" type="OBJ">
+    <token>Nobelpriset</token>
+  </ne>
+  ```
+standard_reference: |-
+    [Dimitrios Kokkinakis, Jyrki Niemi, Sam Hardwick, Krister Lindén, and Lars Borin. 2014. HFST-SweNER — A New NER
+    Resource for Swedish. In Proceedings of the Ninth International Conference on Language Resources and Evaluation
+    (LREC'14), pages 2537-2543, Reykjavik, Iceland. European Language Resources Association
+    (ELRA).](http://www.lrec-conf.org/proceedings/lrec2014/pdf/391_Paper.pdf)
+other_references:
+  - "[Dimitrios Kokkinakis. 2004. Reducing the effect of name explosion](https://demo.spraakbanken.gu.se/svedk/pbl/kokkinakisBNER.pdf)"
+  - "Download HFST-SweNER: https://www.kielipankki.fi/download/HFST-SweNER/"
+tool: "HFST-SweNER"
+model: "Included in the tool"
+trained_on: ''
+tagset: "[Named entity tags from hfst-SweNER](https://svn.spraakdata.gu.se/sb-arkiv/pub/swener-tags.html)"
+evaluation_results: "f-score between 91.33% to 27.48%, depending on the named entity category"
+description:
+  swe: |-
+    Namnigenkänning är en språkteknologisk tekniks som automatiskt känner igen och förser namn och namnliknande uttryck
+    (s.k. entiteter) i löpande text med fördefinierade etiketter, som t. ex. person eller organisationer, men, beroende
+    på tillämpningsområdet, även numeriska uttryck och tidsuttryck. HFST-SweNER bygger på konvertering, modellering och
+    anpassning av en tidigare svenskt NER-system till Helsinki Finite-State Transducer Technology (HFST)-plattformen.
+    HFST-SweNER är en fullfjädrad implementering med öppen källkod som stöder en mängd olika generiska namngivna
+    entitetstyper och består av flera lexikala resurslager såsom olika n-gram-baserade namngivna namnlistor (s.k.
+    gazetteers).
+  eng: |-
+    Named entity recognition (NER) recognises textual mentions of named entities that belong to a predefined set of
+    categories, such as locations, and time expressions. HFST-SweNER is based on the conversion, modelling and
+    adaptation of a Swedish NER system from a hybrid environment to the Helsinki Finite-State Transducer Technology
+    (HFST) platform. HFST-SweNER is a full-fledged open source implementation that supports a variety of generic named
+    entity types and consists of multiple, reusable resource layers such as various n-gram-based named entity lists
+    (gazetteers).
+created: 2014-07-04
+updated: 2020-05-13
diff --git a/sparv/modules/wsd/metadata.yaml b/sparv/modules/wsd/metadata.yaml
@@ -0,0 +1,61 @@
+id: swe-sense-wsd
+name:
+  swe: Betydelsedisambiguering med hjälp av SALDO ID:n
+  eng: Sense disambiguation of SALDO identifiers
+short_description:
+  swe: Ordbetydelsedisambiguering baserad på annotering i SALDO
+  eng: Word sense disambiguation based on SALDO annotation
+task: sense disambiguation
+language_codes:
+  - swe
+keywords:
+  - sense disambiguation
+  - saldo
+annotations:
+  - <token>:wsd.sense
+example_output: |-
+  ```xml
+  <token sense="|den..2:-1.000|">Det</token>
+  <token sense="|finna..1:0.497|finnas..1:0.472|finna..2:0.031|">finns</token>
+  <token sense="|den..1:-1.000|en..2:-1.000|">en</token>
+  <token sense="|fil..4:0.661|fil..5:0.194|fil..1:0.104|fil..2:0.040|fil..3:0.001|">fil</token>
+  <token sense="|i..2:-1.000|">i</token>
+  <token sense="|katalog..1:-1.000|">katalogen</token>
+  <token sense="|på..1:-1.000|">på</token>
+  <token sense="|den..1:-1.000|den..2:-1.000|en..2:-1.000|">den</token>
+  <token sense="|extern..1:-1.000|">externa</token>
+  <token sense="|hårddisk..1:-1.000|">hårddisken</token>
+  <token sense="|">.</token>
+  <token sense="|man..1:-1.000|">Man</token>
+  <token sense="|kunna..1:0.666|kunna..4:0.147|kunna..3:0.110|kunna..2:0.077|">kan</token>
+  <token sense="|använda..1:-1.000|">använda</token>
+  <token sense="|den..1:-1.000|en..2:-1.000|">en</token>
+  <token sense="|fil..2:0.573|fil..4:0.213|fil..1:0.130|fil..5:0.084|fil..3:0.001|">fil</token>
+  <token sense="|för..1:-1.000|för..5:-1.000|för..6:-1.000|för..7:-1.000|för..9:-1.000|">för</token>
+  <token sense="|att..1:-1.000|">att</token>
+  <token sense="|slipa..2:0.832|slipa..1:0.168|">slipa</token>
+  <token sense="|kant..1:-1.000|">kanterna</token>
+  <token sense="|på..1:-1.000|">på</token>
+  <token sense="|bräda..1:0.787|bräde..1:0.213|">brädan</token>
+  <token sense="|">.</token>
+  ```
+standard_reference: 'https://aclanthology.org/N15-1164.pdf'
+other_references:
+  - https://github.com/spraakbanken/sparv-wsd/blob/master/README.pdf
+  - "Sparv wsd: https://github.com/spraakbanken/sparv-wsd"
+tool: "Sparv wsd"
+model: |-
+  - [ALL_512_128_w10_A2_140403_ctx1.bin](https://github.com/spraakbanken/sparv-wsd/blob/master/models/scouse/ALL_512_128_w10_A2_140403_ctx1.bin)  
+  - [lem_cbow0_s512_w10_NEW2_ctx.bin](https://github.com/spraakbanken/sparv-wsd/blob/master/models/scouse/lem_cbow0_s512_w10_NEW2_ctx.bin)
+trained_on: 'SALDO from May 2014 (SCOUSE model)'
+tagset: ''
+evaluation_results: |-
+    Using lemma embeddings:  
+    precision: 0.569 recall: 0.292 f-measure: 0.386
+
+    Using sense embeddings:  
+    precision: 0.667 recall: 0.332 f-measure: 0.443
+
+    More information: https://aclanthology.org/N15-1164.pdf
+created: 2018-05-28
+updated: 2022-05-13