data.yml

datasets:
  alva-manchego-et-al-2020-asset:
    author: Alva-Manchego et al.
    domain: Wikipedia
    instances: 2359 sentences (2000 train, 359 test)
    kind: Parallel
    language: EN
    level: Sentence
    link: https://github.com/facebookresearch/asset
    linkNote: null
    name: ASSET
    paper: https://doi.org/10.18653/v1/2020.acl-main.424
    references: 10
    year: 2020
  attal-et-al-2023-plaba:
    author: Attal et al.
    domain: Medical
    instances: 750 documents with 7643 sentence pairs
    kind: Parallel
    language: EN
    level: Document
    link: https://osf.io/rnpmf/
    linkNote: null
    name: PLABA
    paper: https://www.nature.com/articles/s41597-022-01920-3
    references: 1
    year: 2023
  aumiller-and-gertz-2022-klexikon:
    author: Aumiller and Gertz
    domain: Wikipedia
    instances: 2898 article pairs
    kind: Comparable
    language: DE
    level: Document
    link: https://github.com/dennlinger/klexikon
    linkNote: null
    name: Klexikon
    paper: https://aclanthology.org/2022.lrec-1.288/
    references: 1
    year: 2022
  battisti-et-al-2020-simplegerman-v2.0:
    author: Battisti et al.
    domain: Web
    instances: 5461 simple, unaligned documents and 378 aligned (complex-simple) documents (6217 docs in total). The document-aligned portion has 17,121 complex sentences and 21,072 simple sentences. No statistics on the sentence-alignments are reported.
    kind: Comparable
    language: DE
    level: Document
    link: null
    linkNote: '[Scraping code](https://zenodo.org/record/4507047)'
    name: SimpleGerman V2.0
    paper: https://aclanthology.org/2020.lrec-1.404
    references: 1
    year: 2020
  botha-et-al-2018-wikisplit:
    author: Botha et al.
    domain: Wikipedia
    instances: 1 million sentences
    kind: Parallel
    language: EN
    level: Sentence
    link: https://github.com/google-research-datasets/wiki-split
    linkNote: null
    name: WikiSplit
    paper: https://aclanthology.org/D18-1080/
    references: 1
    year: 2018
  campillos-llanos-et-al-2022-clara-med:
    author: Campillos-Llanos et al.
    domain: Medical
    instances: 24298 comparable documents and 3800 parallel sentences
    kind: Comparable
    language: ES
    level: Document
    link: https://digital.csic.es/handle/10261/269887
    linkNote: null
    name: CLARA-MeD
    paper: http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/view/6439
    references: null
    year: 2022
  campillos-llanos-et-al-2024-clara-med:
    author: Campillos-Llanos et al.
    domain: Medical
    instances: 1200 manually-simplified sentences
    kind: Parallel
    language: ES
    level: Sentence
    link: https://digital.csic.es/handle/10261/346579
    linkNote: null
    name: CLARA-MeD-simp-sent
    paper: http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/download/6576/3976
    references: 1
    year: 2024
  campillos-llanos-et-al-2024-simpmedlexsp:
    author: Campillos-Llanos et al.
    domain: Medical
    instances: ">14000 pairs of medical terms and the corresponding simplified synonym/definition."
    kind: Parallel
    language: ES
    level: Lexical
    link: https://digital.csic.es/handle/10261/349662
    linkNote: null
    name: SimpMedLexSp
    paper: https://aclanthology.org/2024.lrec-main.1216.pdf
    references: 1
    year: 2024
  cao-et-al-2020-msd-manuals:
    author: Cao et al.
    domain: Medical
    instances: 2551 linked paragraphs (professionals <-> laymen) with average of 10.4 and 11.3 sentences each. From a random sample of 1000 paragraphs, medical experts extracted  930 aligned sentences with equivalent meaning.
    kind: Comparable
    language: EN
    level: Sentence
    link: https://srhthu.github.io/expertise-style-transfer/#introduction
    linkNote: null
    name: MSD-Manuals
    paper: https://doi.org/10.18653/v1/2020.acl-main.100
    references: 1
    year: 2020
  chamovitz-and-abend-2022-festability:
    author: Chamovitz and Abend
    domain: Talks
    instances: 321 sentence pairs
    kind: Parallel
    language: EN
    level: Sentence
    link: https://github.com/eytan-c/CognitiveSimplification
    linkNote: null
    name: FestAbility
    paper: https://aclanthology.org/2022.conll-1.17/
    references: 1
    year: 2022
  coster-and-kauchak-2011-c&k1:
    author: Coster and Kauchak
    domain: Wikipedia
    instances: 137,000 paired sentences from 10,588 articles.
    kind: Comparable
    language: EN
    level: Sentence
    link: https://cs.pomona.edu/~dkauchak/simplification/
    linkNote: null
    name: C&K1
    paper: https://aclanthology.org/P11-2117
    references: 1
    year: 2011
  devaraj-et-al-2021-cochrane:
    author: Devaraj et al.
    domain: Medical
    instances: 4459 paragraph pairs (<1024 tokens)
    kind: Comparable
    language: EN
    level: Paragraph
    link: https://github.com/AshOlogn/Paragraph-level-Simplification-of-Medical-Texts
    linkNote: null
    name: Cochrane
    paper: https://aclanthology.org/2021.naacl-main.395
    references: 1
    year: 2021
  dmitrieva-and-tiedemann-2021-ruadapt:
    author: Dmitrieva and Tiedemann
    domain: Books
    instances: 457 documents
    kind: Parallel
    language: RU
    level: Document
    link: https://github.com/Digital-Pushkin-Lab/RuAdapt
    linkNote: null
    name: RuAdapt
    paper: https://aclanthology.org/2021.bsnlp-1.8
    references: null
    year: 2021
  ganitkevitch-et-al-2013-ppdb:
    author: Ganitkevitch et al.
    domain: Mixed
    instances: 221 million sentences
    kind: Comparable
    language: EN
    level: Sentence
    link: http://paraphrase.org
    linkNote: null
    name: PPDB
    paper: https://aclanthology.org/N13-1092/
    references: 1
    year: 2013
  goldsack-et-al-2022-biolaysumm:
    author: Goldsack et al.
    domain: Medical
    instances: 32353 document-plain abstract pairs
    kind: Parallel
    language: EN
    level: Document
    link: https://github.com/TGoldsack1/Corpora_for_Lay_Summarisation
    linkNote: null
    name: BioLaySumm
    paper: https://aclanthology.org/2022.emnlp-main.724/
    references: 1
    year: 2022
  grabar-and-cardon-2019-clear:
    author: Grabar and Cardon
    domain: Medical
    instances: 16190 documents
    kind: Comparable
    language: FR
    level: Document
    link: http://natalia.grabar.free.fr/resources.php
    linkNote: null
    name: CLEAR
    paper: https://aclanthology.org/W18-7002/
    references: 1
    year: 2019
  guo-et-al-2022-cells:
    author: Guo et al.
    domain: Medical
    instances: 63000
    kind: Comparable
    language: EN
    level: Paragraph
    link: https://github.com/linguisticanomalies/pls_retrieval
    linkNote: null
    name: CELLS
    paper: https://arxiv.org/abs/2211.03818
    references: 1
    year: 2022
  hauser-et-al-2022-sniml:
    author: Hauser et al.
    domain: News
    instances: 13,447 documents
    kind: Simplified only
    language: DE, EN, FI, FR, IT, SV
    level: Document
    link: https://pub.cl.uzh.ch/projects/sniml/en/read/
    linkNote: null
    name: SNIML
    paper: https://aclanthology.org/2022.readi-1.4
    references: n/a
    year: 2022
  horiguchi-et-al-2024-jasmine:
    author: Horiguchi et al.
    domain: Medical
    instances: 1425 sentences (0/425/1000 train/val/test)
    kind: Parallel
    language: JA
    level: Sentence
    link: https://github.com/OnizukaLab/JASMINE
    linkNote: available on request
    name: JASMINE
    paper: https://aclanthology.org/2024.naacl-srw.23/
    references: 1
    year: 2024
  hwang-et-al-2015-ew-sew:
    author: Hwang et al.
    domain: Wikipedia
    instances: 150,000 full and 130,000 partial matches
    kind: Comparable
    language: EN
    level: Sentence
    link: https://web.archive.org/web/20150906192742/http://ssli.ee.washington.edu/tial/projects/simplification/
    linkNote: 'Archived, pre-processed version available [here](https://github.com/senisioi/NeuralTextSimplification)'
    name: EW-SEW
    paper: https://aclanthology.org/N15-1022/
    references: 1
    year: 2015
  jiang-et-al-2020-newsela-auto:
    author: Jiang et al.
    domain: News
    instances: 666,645 sentence pairs from 1932 articles at 5 levels
    kind: Parallel
    language: EN
    level: Sentence
    link: https://github.com/chaojiang06/wiki-auto
    linkNote: null
    name: Newsela-AUTO
    paper: https://doi.org/10.18653/v1/2020.acl-main.709
    references: 1
    year: 2020
  jiang-et-al-2020-wiki-auto:
    author: Jiang et al.
    domain: Wikipedia
    instances: 488,332 train sentences from 138,095 article pairs (2019/09 dump).
    kind: Comparable
    language: EN
    level: Sentence
    link: https://github.com/chaojiang06/wiki-auto
    linkNote: 'Part of [GEM](https://gem-benchmark.com/data_cards/Wiki-Auto)'
    name: Wiki-AUTO
    paper: https://doi.org/10.18653/v1/2020.acl-main.709
    references: 1
    year: 2020
  kajiwara-and-komachi-2016-sscorpus:
    author: Kajiwara and Komachi
    domain: Wikipedia
    instances: 492,993 aligned sentences from 126K article pairs.
    kind: Comparable
    language: EN
    level: Sentence
    link: https://github.com/tmu-nlp/sscorpus
    linkNote: null
    name: sscorpus
    paper: https://aclanthology.org/C16-1109
    references: 1
    year: 2016
  kauchak-2013-c&k-2:
    author: Kauchak
    domain: Wikipedia
    instances: 167,000 paired sentences.
    kind: Comparable
    language: EN
    level: Sentence
    link: https://cs.pomona.edu/~dkauchak/simplification/
    linkNote: null
    name: C&K-2
    paper: https://aclanthology.org/P13-1151
    references: 1
    year: 2013
  klaper-et-al-2013-simplegerman-:
    author: Klaper et al.
    domain: Web
    instances: 7000 sentences from 256 articles. 78% of sentences have an alignment
    kind: Comparable
    language: DE
    level: Sentence
    link: null
    linkNote: Available on request
    name: SimpleGerman
    paper: http://www.aclweb.org/anthology/W13-2902
    references: 1
    year: 2013
  "klerke-and-sogaard-2012-dsim":
    author: "Klerke and Søgaard"
    domain: News
    instances: 3,701 articles with 48,186 aligned sentences
    kind: Parallel
    language: DA
    level: Document
    link: null
    linkNote: null
    name: Dsim
    paper: https://aclanthology.org/L12-1113/
    references: 1
    year: 2012
  li-et-al-2020-pharmmt:
    author: 'Li et al. '
    domain: Medical
    instances: 380,000K aligned sentences.
    kind: Parallel
    language: EN
    level: Sentence
    link: null
    linkNote: null
    name: PharmMT
    paper: https://doi.org/10.18653/v1/2020.findings-emnlp.251
    references: 1
    year: 2020
  luo-et-al-2022-medlane:
    author: Luo et al.
    domain: Clinical
    instances: 12,801/1,015/1,016 train/valid/test sentences (avg. 20/24 tokens in source/target)
    kind: Parallel
    language: EN
    level: Sentence
    link: https://github.com/machinelearning4health/MedLane
    linkNote: null
    name: MedLane
    paper: https://aclanthology.org/2022.coling-1.313
    references: 1
    year: 2022
  moramarco-et-al-2022-mtsamples:
    author: Moramarco et al.
    domain: Clinical
    instances: 1250 sentence pairs.
    kind: Parallel
    language: EN
    level: Sentence
    link: https://github.com/babylonhealth/laymaker
    linkNote: null
    name: MTSamples
    paper: https://arxiv.org/abs/2112.12672
    references: 1
    year: 2022
  narayan-et-al-2017-websplit:
    author: Narayan et al.
    domain: Mixed
    instances: 1 million sentences
    kind: Comparable
    language: EN
    level: Sentence
    link: https://github.com/shashiongithub/Split-and-Rephrase
    linkNote: null
    name: WebSplit
    paper: https://doi.org/10.18653/v1/d17-1064
    references: 1
    year: 2017
  pavlick-and-callison-burch-2016-simple-ppdb:
    author: Pavlick and Callison-Burch
    domain: Mixed
    instances: 4.5 million sentences
    kind: Comparable
    language: EN
    level: Sentence
    link: https://www.seas.upenn.edu/~nlp/resources/simple-ppdb.tgz
    linkNote: null
    name: Simple-PPDB
    paper: https://doi.org/10.18653/v1/p16-2024
    references: 1
    year: 2016
  rios-et-al-2021-20-minutes:
    author: Rios et al.
    domain: News
    instances: 18,305 articles with simplified summaries.
    kind: Parallel
    language: DE
    level: Document
    link: https://github.com/ZurichNLP/20Minuten
    linkNote: null
    name: 20 minutes
    paper: https://doi.org/10.18653/v1/2021.newsum-1.16
    references: 1
    year: 2021
  scarton-et-al-2018-simpa:
    author: Scarton et al.
    domain: Web
    instances: 1100 sentences with 3 lexical, and one 1 syntactic simplification each
    kind: Parallel
    language: EN
    level: Sentence
    link: https://github.com/SIMPATICOProject/simpa
    linkNote: null
    name: SimPA
    paper: https://aclanthology.org/L18-1685/
    references: '3, 1'
    year: 2018
  sulem-et-al-2018-hsplit:
    author: Sulem et al.
    domain: Wikipedia
    instances: 359 sentences (test set of turk corpus)
    kind: Parallel
    language: EN
    level: Sentence
    link: https://github.com/eliorsulem/HSplit-corpus
    linkNote: null
    name: Hsplit
    paper: https://doi.org/10.18653/v1/D18-1081
    references: 4
    year: 2018
  taylor-et-al-2022-psat:
    author: Taylor et al.
    domain: Education
    instances: 112 documents, with total of 1883 aligned sentences
    kind: Parallel
    language: EN
    level: Document
    link: https://zenodo.org/record/7065615
    linkNote: null
    name: PSAT
    paper: https://aclanthology.org/2022.coling-1.566/
    references: 1
    year: 2022
  toborek-et-al-2022-simple-german-v3.0:
    author: Toborek et al.
    domain: Web
    instances: 708 documents
    kind: Comparable
    language: DE
    level: Document
    link: null
    linkNote: '[Scraping code](https://github.com/buschmo/Simple-German-Corpus)'
    name: Simple German V3.0
    paper: https://arxiv.org/abs/2209.01106
    references: 1
    year: 2022
  trienes-et-al-2022-simple-patho:
    author: Trienes et al.
    domain: Clinical
    instances: 851 documents
    kind: Parallel
    language: DE
    level: Document
    link: null
    linkNote: null
    name: SimplePatho
    paper: https://aclanthology.org/2022.tsar-1.3/
    references: 1
    year: 2022
  vajjala-and-lucic-2018-onestopenglish:
    author: Vajjala and Lucic
    domain: News
    instances: '189 articles at three levels. Automatic sentence alignment: 1.6K ELE-INT, 2.1K ELE-ADV, 3.1K INT-ADV.'
    kind: Parallel
    language: EN
    level: Document
    link: https://zenodo.org/record/1219041
    linkNote: null
    name: OneStopEnglish
    paper: https://doi.org/10.18653/v1/w18-0535
    references: 1
    year: 2018
  van-den-bercken-et-al-2019-mytomorrows-wiki:
    author: van den Bercken et al.
    domain: Medical
    instances: "5415 (manually aligned); 3797 (automatically aligned)"
    kind: Comparable
    language: EN
    level: Sentence
    link: https://github.com/myTomorrows-research/public/tree/5b054a88746b7d4422732e2fd3ee6a77a8a53918/WWW2019
    linkNote: null
    name: myTomorrows-Wiki
    paper: https://doi.org/10.1145/3308558.3313630
    references: 1
    year: 2019
  van-et-al-2020-automets:
    author: Van et al.
    domain: Medical
    instances: 3300 aligned sentences
    kind: Comparable
    language: EN
    level: Sentence
    link: https://github.com/vanh17/MedTextSimplifier/tree/master/data_processing/data
    linkNote: null
    name: AutoMeTS
    paper: https://doi.org/10.18653/v1/2020.coling-main.122
    references: 1
    year: 2020
  xu-et-al-2015-newsela:
    author: Xu et al.
    domain: News
    instances: 1130 articles (original); 1911 articles (v2016-01-29); at 5 levels
    kind: Parallel
    language: EN
    level: Document
    link: https://newsela.com/data/
    linkNote: null
    name: Newsela
    paper: https://doi.org/10.1162/tacl_a_00139
    references: 1
    year: 2015
  xu-et-al-2015-newsela-es:
    author: Xu et al.
    domain: News
    instances: 243 articles (v2016-01-29) at 5 levels
    kind: Parallel
    language: ES
    level: Document
    link: https://newsela.com/data/
    linkNote: null
    name: Newsela-ES
    paper: https://doi.org/10.1162/tacl_a_00139
    references: 1
    year: 2015
  xu-et-al-2016-turkcorpus:
    author: Xu et al.
    domain: Wikipedia
    instances: 2359 sentences (2000 dev, 359 test)
    kind: Parallel
    language: EN
    level: Sentence
    link: https://github.com/cocoxu/simplification/
    linkNote: null
    name: TurkCorpus
    paper: https://doi.org/10.1162/tacl_a_00107
    references: 8
    year: 2016
  zhang-and-lapata-2017-wikilarge:
    author: Zhang and Lapata
    domain: Wikipedia
    instances: 296,402 sentence pairs (WikiLarge)
    kind: Comparable
    language: EN
    level: Sentence
    link: https://github.com/XingxingZhang/dress
    linkNote: null
    name: WikiLarge
    paper: https://doi.org/10.18653/v1/d17-1062
    references: 1
    year: 2017
  zhang-and-lapata-2017-wikismall:
    author: Zhang and Lapata
    domain: Wikipedia
    instances: 89,042 sentence pairs
    kind: Comparable
    language: EN
    level: Sentence
    link: https://github.com/XingxingZhang/dress
    linkNote: null
    name: WikiSmall
    paper: https://doi.org/10.18653/v1/d17-1062
    references: 1
    year: 2017
  zhu-et-al-2010-pwkp:
    author: Zhu et al.
    domain: Wikipedia
    instances: 108,016 paired sentences extracted from 65,133 articles.
    kind: Comparable
    language: EN
    level: Sentence
    link: https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/2447
    linkNote: null
    name: PWKP
    paper: https://aclanthology.org/C10-1152
    references: 1
    year: 2010
  horn-etal-2014-learning:
    author: Horn et al.
    domain: Wikipedia
    instances: 500
    kind: Parallel
    language: EN
    level: Lexical
    link: https://cs.pomona.edu/~dkauchak/simplification/
    linkNote:
    name: LexMTurk
    paper: https://aclanthology.org/P14-2075/
    references: multiple
    year: 2014
  paetzold-specia-2016b:
    author: Paetzold and Specia
    domain: Wikipedia
    instances: 239
    kind: Comparable
    language: EN
    level: Lexical
    link: https://zenodo.org/record/2552381#.Y2ququzP0-R
    linkNote:
    name: NNSEval
    paper: https://ojs.aaai.org/index.php/AAAI/article/view/9885
    references: multiple
    year: 2016
  paetzold-specia-2016-benchmarking:
    author: Paetzold and Specia
    domain: Wikipedia
    instances: 929
    kind: Comparable
    language: EN
    level: Lexical
    link: http://ghpaetzold.github.io/data/BenchLS.zip
    linkNote:
    name: BenchLS
    paper: https://aclanthology.org/L16-1491/
    references: multiple
    year: 2016
  uchida-etal-2018-cefr:
    author: Uchida et al.
    domain: Education
    instances: 414
    kind: Comparable
    language: EN
    level: Lexical
    link: http://www-bigdata.ist.osaka-u.ac.jp/arase/pj/lex-simplification.zip
    linkNote:
    name: CEFR
    paper: https://aclanthology.org/L18-1514/
    references: 2.4(avg)
    year: 2018
  alarcon-etal-2021:
    author: Alarcon et al.
    domain: Mixed
    instances: 5153
    kind: Parallel
    language: ES
    level: Lexical
    link: https://github.com/LURMORENO/EASIER_CORPUS
    linkNote:
    name: EASIER
    paper: https://ieeexplore.ieee.org/document/9400837
    references: 1-3
    year: 2021
  hartmann-aluisio-2021:
    author: Hartmann and Aluisio
    domain: Education
    instances: 1582
    kind: Parallel
    language: PT (BR)
    level: Lexical
    link: https://github.com/nathanshartmann/SIMPLEX-PB-3.0
    linkNote:
    name: SIMPLEX-PB-3.0
    paper: https://linguamatica.com/index.php/linguamatica/article/view/323
    references: 7,3(avg)
    year: 2021
  sun-etal-2021-document:
    author: Sun et al.
    domain: Wikipedia
    instances: 143,546 article pairs
    kind: Comparable
    language: EN
    level: Document
    link: https://github.com/RLSNLP/Document-level-text-simplification/tree/main/Dataset
    linkNote: null
    name: D-Wikipedia
    paper: https://doi.org/10.18653/v1/2021.emnlp-main.630
    references: 1
    year: 2021
  sun-etal-2020-helpfulness:
    author: Sun et al.
    domain: Wikipedia
    instances: 116,020 sentences with context (includes preceding and following sentence)
    kind: Comparable
    language: EN
    level: Sentence
    link: https://github.com/rlsnlp/document-context-to-sentence-simplification
    linkNote: null
    name: Wikipedia (with context)
    paper: https://doi.org/10.18653/v1/2020.coling-main.121
    references: 1
    year: 2020
  lee-vajjala-2022-neural:
    author: Lee and Vajjala
    domain: Education
    instances: 6165 (for each language)
    kind: Parallel
    language: EN / FR
    level: Document
    link: https://zenodo.org/record/6327828
    linkNote: null
    name: Vikidia
    paper: https://doi.org/10.18653/v1/2022.findings-acl.300
    references: 1
    year: 2022
  arase-etal-2022-cefr:
    author: Arase et al.
    domain: Education
    instances: 17000 sentences from Newsela-Auto (upon request), Wiki-Auto, and SCoRE dataset
    kind: CEFR-level
    language: EN
    level: Sentence
    link: https://github.com/yukiar/CEFR-SP
    linkNote: null
    name: CEFR-SP
    paper: https://doi.org/10.18653/v1/2022.emnlp-main.416
    references: 1
    year: 2022
  joseph-etal-2023-cochrane:
    author: Joseph et al.
    domain: Medical
    instances: Cross-lingual pairs; 5K pairs (clean, semi-automatically aligned), 100K pairs (noisy)
    kind: Comparable
    language: EN, ES, FR, FA
    level: Sentence
    link: https://github.com/SebaJoe/MultiCochrane
    linkNote: null
    name: MultiCochrane
    paper: https://doi.org/10.18653/v1/2023.emnlp-main.1037
    references: 1
    year: 2023
  laban-etal-2023-swipe:
    author: Laban et al.
    domain: Wikipedia
    instances: 145,161 article revision pairs, anntations of fine-grained edit operations on ~5000 articles
    kind: Comparable
    language: EN
    level: Document
    link: https://github.com/Salesforce/simplification
    linkNote: null
    name: SWiPE
    paper: https://doi.org/10.18653/v1/2023.acl-long.596
    references: 1
    year: 2023
  stodden-etal-2023-deplain:
    author: Stodden et al.
    domain: News
    instances: 500 document pairs in News domain (13k aligned sentences), 150 document pairs in Web domain (2k aligned sentences)
    kind: Parallel
    language: DE
    level: Document
    link: https://github.com/rstodden/DEPlain
    linkNote: null
    name: DEplain
    paper: https://doi.org/10.18653/v1/2023.acl-long.908
    references: 1
    year: 2023