From ec20beb952b6209ad29020867555f6b5f330ae33 Mon Sep 17 00:00:00 2001 From: Martin Hammarstedt Date: Tue, 11 Feb 2025 14:26:32 +0100 Subject: [PATCH] Update analysis metadata --- sparv/modules/geo/metadata.yaml | 4 +- sparv/modules/hunpos/metadata.yaml | 47 ++++++++------ sparv/modules/lexical_classes/metadata.yaml | 8 ++- sparv/modules/malt/metadata.yaml | 10 +-- sparv/modules/phrase_structure/metadata.yaml | 1 - sparv/modules/readability/metadata.yaml | 1 - sparv/modules/saldo/metadata.yaml | 4 +- sparv/modules/segment/metadata.yaml | 19 +++--- sparv/modules/sensaldo/metadata.yaml | 4 +- sparv/modules/stanza/metadata.yaml | 65 ++++++++++++-------- sparv/modules/swener/metadata.yaml | 10 ++- sparv/modules/wsd/metadata.yaml | 17 ++--- sparv/modules/xml_export/metadata.yaml | 1 - 13 files changed, 111 insertions(+), 80 deletions(-) diff --git a/sparv/modules/geo/metadata.yaml b/sparv/modules/geo/metadata.yaml index 19d4b758..95fcbcc7 100644 --- 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 index 4b8c7cc4..5f9485c2 100644 --- 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: |- korpus . ``` -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: |- korpus . ``` -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 --- @@ -163,11 +169,14 @@ 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 @@ -175,7 +184,7 @@ description: 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 index 866d3794..1063017f 100644 --- 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 index ff73f82f..644ae3c3 100644 --- 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 index 5e2a83b4..2cb50f1a 100644 --- 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 index 56cd61a4..d4112018 100644 --- 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 index 80ade651..33fdca3c 100644 --- 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 index 87e14ad8..eb515ca3 100644 --- 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: |- . ``` 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: |- . ``` -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 index f57e276e..458a5896 100644 --- 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: '' diff --git a/sparv/modules/stanza/metadata.yaml b/sparv/modules/stanza/metadata.yaml index 3df1c333..0229f337 100644 --- a/sparv/modules/stanza/metadata.yaml +++ b/sparv/modules/stanza/metadata.yaml @@ -1,14 +1,13 @@ -id: stanza-parent-swe +id: stanza-swe-parent abstract: true language_codes: - swe keywords: - stanza -tool: - name: "Stanza" - url: "https://stanfordnlp.github.io/stanza/" -licences: - tool: "Apache License 2.0" +tools: + - name: "Stanza" + url: "https://stanfordnlp.github.io/stanza/" + license: "Apache License 2.0" trained_on: "[SUC3](https://spraakbanken.gu.se/resurser/suc3), [TalbankenSBX](https://spraakbanken.gu.se/resurser/talbanken), [SIC2](https://spraakbanken.gu.se/resurser/sic2)" other_references: - "Stanza: Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton and Christopher D. Manning. 2020" @@ -32,7 +31,7 @@ created: 2020-12-07 updated: 2022-08-10 --- id: sbx-swe-pos-stanza-stanzamorph -parent: stanza-parent-swe +parent: stanza-swe-parent name: swe: SUC-ordklasstaggning med Stanza eng: SUC part-of-speech tagging with Stanza @@ -60,7 +59,7 @@ description: [Sparv](https://spraakbanken.gu.se/sparv). --- id: sbx-swe-msd-stanza-stanzamorph-suc3 -parent: stanza-parent-swe +parent: stanza-swe-parent name: swe: Morfosyntaktisk SUC-taggning med Stanza eng: Tagging of morphological features (SUC) by Stanza @@ -80,7 +79,10 @@ example_output: |- korpus . ``` -model: "[Stanzamorph](https://spraakbanken.gu.se/resurser/stanzamorph)" +models: + - name: Stanzamorph + url: https://spraakbanken.gu.se/resurser/stanzamorph + license: CC BY 4.0 description: eng: |- This annotation contains morphosyntactic features in addition to part-of-speech tags. @@ -91,7 +93,7 @@ description: [Sparv](https://spraakbanken.gu.se/sparv). --- id: sbx-swe-msd-stanza-stanzamorph-ufeats -parent: stanza-parent-swe +parent: stanza-swe-parent name: swe: Morfologisk analys för svenska baserad på Stanza eng: Stanza-based morphological analysis for Swedish @@ -115,7 +117,10 @@ other_references: - "Stanza: A Python Natural Language Processing Toolkit for Many Human Languages. In Association for Computational Linguistics (ACL) System Demonstrations. 2020" - "TalbankenSBX: https://spraakbanken.gu.se/en/blog/20200609-the-five-lives-of-talbanken" - "SIC2: https://spraakbanken.gu.se/en/resources/sic2" -model: "[Stanzamorph](https://spraakbanken.gu.se/resurser/stanzamorph)" +models: + - name: Stanzamorph + url: https://spraakbanken.gu.se/resurser/stanzamorph + license: CC BY 4.0 tagset: "[UD](https://universaldependencies.org/u/feat/index.html)" evaluation_results: '' description: @@ -125,7 +130,7 @@ description: This analysis uses universal features, defined as part of the Universal Dependencies standard. --- id: sbx-swe-lemmatization-stanza-stanzalem -parent: stanza-parent-swe +parent: stanza-swe-parent name: swe: SUC3-grundformanalys med Stanza eng: SUC3-citation form analysis with Stanza @@ -148,18 +153,21 @@ other_references: - "Stanza: Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton and Christopher D. Manning. 2020" - "Stanza: A Python Natural Language Processing Toolkit for Many Human Languages. In Association for Computational Linguistics (ACL) System Demonstrations. 2020" - "SUC3: https://spraakbanken.gu.se/en/resources/suc3" -model: "[Stanzalem](https://spraakbanken.gu.se/resurser/stanzalem)" +models: + - name: Stanzalem + url: https://spraakbanken.gu.se/resurser/stanzalem + license: CC BY 4.0 trained_on: "[SUC3](https://spraakbanken.gu.se/resurser/suc3)" evaluation_results: Accuracy = 0.99 description: eng: |- - In 2020, the Stanza tool was trained and tested the SUC3 corpus in order to create a high-quality analysis. + In 2020, the Stanza tool was trained and tested on the SUC3 corpus in order to create a high-quality analysis. Currently (in 2024), this analysis is available in Sparv, but it is not provided by default, since it is not fully compatible with SALDO-style lemmas. This model's advantage is that it can be used to lemmatize any token, including out-of-vocabulary tokens. --- id: sbx-swe-dependency-stanza-stanzasynt -parent: stanza-parent-swe +parent: stanza-swe-parent name: swe: Dependensparsning med Stanza eng: Dependency parsing with Stanza @@ -180,7 +188,10 @@ example_output: |- korpus . ``` -model: "[Stanzasynt](https://spraakbanken.gu.se/resurser/stanzasynt)" +models: + - name: Stanzasynt + url: https://spraakbanken.gu.se/resurser/stanzasynt + license: CC BY 4.0 trained_on: "[TalbankenSBX](https://spraakbanken.gu.se/resurser/talbanken)" tagset: "[MambaDep](https://svn.spraakdata.gu.se/sb-arkiv/pub/mamba.html)" evaluation_results: |- @@ -191,7 +202,7 @@ description: In 2020, the Stanza tool was trained and tested on TalbankenSBX (following MambaDep-style annotation) in order to create a high-quality analysis. Currently (in 2024), this is the default analysis for Swedish in Sparv --- -id: stanza-parent-eng +id: stanza-eng-parent abstract: true language_codes: - eng @@ -203,12 +214,14 @@ other_references: - "Stanza: Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton and Christopher D. Manning. 2020" - "Stanza: A Python Natural Language Processing Toolkit for Many Human Languages. In Association for Computational Linguistics (ACL) System Demonstrations. 2020" evaluation_results: '' -model: Stanza standard model for English (https://stanfordnlp.github.io/stanza/models.html) +models: + - name: Stanza standard model for English + url: https://stanfordnlp.github.io/stanza/models.html created: 2022-08-10 updated: 2022-08-10 --- id: sbx-eng-pos-stanza -parent: stanza-parent-eng +parent: stanza-eng-parent name: swe: Ordklasstaggning med Stanza för engelska eng: Part-of-speech tagging with Stanza for English @@ -235,7 +248,7 @@ example_extra: |- ``` --- id: sbx-eng-sentence-stanza -parent: stanza-parent-eng +parent: stanza-eng-parent name: swe: Meningssegmentering för engelska med Stanza eng: Sentence segmentation for English with Stanza @@ -277,7 +290,7 @@ example_extra: |- ``` --- id: sbx-eng-tokenization-stanza -parent: stanza-parent-eng +parent: stanza-eng-parent name: swe: Tokenisering för engelska med Stanza eng: Tokenization for English with Stanza @@ -306,7 +319,7 @@ example_extra: |- ``` --- id: sbx-eng-lemmatization-stanza -parent: stanza-parent-eng +parent: stanza-eng-parent name: swe: Lemmatisering för engelska med Stanza eng: Lemmatization for English with Stanza @@ -335,7 +348,7 @@ example_extra: |- ``` --- id: sbx-eng-dependency-stanza -parent: stanza-parent-eng +parent: stanza-eng-parent name: swe: Dependensparsning för engelska med Stanza eng: Dependency parsing for English with Stanza @@ -367,7 +380,7 @@ example_extra: |- ``` --- id: sbx-eng-namedentity-stanza -parent: stanza-parent-eng +parent: stanza-eng-parent name: swe: Namnigenkänning för engelska med Stanza eng: Named entity recognition for English with Stanza @@ -419,7 +432,7 @@ description: geographical locations) in the text. --- id: sbx-eng-pos-stanza-upos -parent: stanza-parent-eng +parent: stanza-eng-parent name: swe: UD-Ordklasstaggning med Stanza för engelska eng: UD part-of-speech tagging with Stanza for English @@ -446,7 +459,7 @@ example_extra: |- ``` --- id: sbx-eng-msd-stanza-ufeats -parent: stanza-parent-eng +parent: stanza-eng-parent name: swe: Morfologisk analys för engelska baserad på Stanza eng: Stanza-based morphological analysis for English diff --git a/sparv/modules/swener/metadata.yaml b/sparv/modules/swener/metadata.yaml index 244aca69..3105ffd3 100644 --- a/sparv/modules/swener/metadata.yaml +++ b/sparv/modules/swener/metadata.yaml @@ -57,12 +57,10 @@ standard_reference: |- 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: - name: "HFST-SweNER" - url: "https://www.kielipankki.fi/download/HFST-SweNER/" -licences: - tool: CC-BY -model: "Included in the tool" +tools: + - name: "HFST-SweNER" + url: "https://www.kielipankki.fi/download/HFST-SweNER/" + license: CC-BY 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" diff --git a/sparv/modules/wsd/metadata.yaml b/sparv/modules/wsd/metadata.yaml index 63e3392d..acdd7020 100644 --- a/sparv/modules/wsd/metadata.yaml +++ b/sparv/modules/wsd/metadata.yaml @@ -42,14 +42,15 @@ 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: - name: Sparv wsd - url: https://github.com/spraakbanken/sparv-wsd -licences: - tool: MIT License -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) +tools: + - name: Sparv wsd + url: https://github.com/spraakbanken/sparv-wsd + license: MIT License +models: + - name: ALL_512_128_w10_A2_140403_ctx1.bin + url: https://github.com/spraakbanken/sparv-wsd/blob/master/models/scouse/ALL_512_128_w10_A2_140403_ctx1.bin + - name: lem_cbow0_s512_w10_NEW2_ctx.bin + url: 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: |- diff --git a/sparv/modules/xml_export/metadata.yaml b/sparv/modules/xml_export/metadata.yaml index eab0ab45..f2ecba3f 100644 --- a/sparv/modules/xml_export/metadata.yaml +++ b/sparv/modules/xml_export/metadata.yaml @@ -6,7 +6,6 @@ keywords: [] example_extra: '' standard_reference: '' other_references: [] -model: '' trained_on: '' tagset: '' evaluation_results: ''