{"id":"https://openalex.org/W2976410295","doi":"https://doi.org/10.18653/v1/w19-8615","title":"MinWikiSplit: A Sentence Splitting Corpus with Minimal Propositions","display_name":"MinWikiSplit: A Sentence Splitting Corpus with Minimal Propositions","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2976410295","doi":"https://doi.org/10.18653/v1/w19-8615","mag":"2976410295"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-8615","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-8615","pdf_url":"https://www.aclweb.org/anthology/W19-8615.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Natural Language Generation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-8615.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090716815","display_name":"Christina Niklaus","orcid":"https://orcid.org/0000-0001-9344-8127"},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Christina Niklaus","raw_affiliation_strings":["University of St Gallen\u2003"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of St Gallen\u2003","institution_ids":["https://openalex.org/I202963720"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053978668","display_name":"Andr\u00e9 Freitas","orcid":"https://orcid.org/0000-0002-4430-4837"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Freitas","raw_affiliation_strings":["University of Manchester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Manchester","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024322708","display_name":"Siegfried Handschuh","orcid":"https://orcid.org/0000-0002-6195-9034"},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Siegfried Handschuh","raw_affiliation_strings":["University Of Passau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Of Passau","institution_ids":["https://openalex.org/I186354981"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"118","last_page":"123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.8429964780807495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7567936778068542},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7408465147018433},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6225915551185608},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6177349090576172},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5607408285140991},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5471739172935486},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5200552344322205},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45403337478637695},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3250349760055542},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06845155358314514}],"concepts":[{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.8429964780807495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7567936778068542},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7408465147018433},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6225915551185608},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6177349090576172},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5607408285140991},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5471739172935486},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5200552344322205},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45403337478637695},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3250349760055542},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06845155358314514},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.18653/v1/w19-8615","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-8615","pdf_url":"https://www.aclweb.org/anthology/W19-8615.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Natural Language Generation","raw_type":"proceedings-article"},{"id":"pmh:oai:www.alexandria.unisg.ch:258308","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400650","display_name":"Alexandria (UniSG) (University of St.Gallen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210158813","host_organization_name":"St.Gallen University of Teacher Education","host_organization_lineage":["https://openalex.org/I4210158813"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:arXiv.org:1909.12131","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.12131","pdf_url":"https://arxiv.org/pdf/1909.12131","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2976410295","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1909.12131.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1909.12131","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1909.12131","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-8615","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-8615","pdf_url":"https://www.aclweb.org/anthology/W19-8615.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Natural Language Generation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2976410295.pdf","grobid_xml":"https://content.openalex.org/works/W2976410295.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1746111881","https://openalex.org/W1872907992","https://openalex.org/W1968548280","https://openalex.org/W2025746854","https://openalex.org/W2037789405","https://openalex.org/W2078861993","https://openalex.org/W2101105183","https://openalex.org/W2109802560","https://openalex.org/W2138238299","https://openalex.org/W2251061338","https://openalex.org/W2462123276","https://openalex.org/W2608265559","https://openalex.org/W2743653651","https://openalex.org/W2804491852","https://openalex.org/W2890771450","https://openalex.org/W2951251261","https://openalex.org/W2954298948","https://openalex.org/W2962899377","https://openalex.org/W2963732644","https://openalex.org/W2964085347","https://openalex.org/W2978670439"],"related_works":["https://openalex.org/W2995488541","https://openalex.org/W2266122193","https://openalex.org/W3195869210","https://openalex.org/W3134942116","https://openalex.org/W2968387840","https://openalex.org/W2739007515","https://openalex.org/W1973452472","https://openalex.org/W1573537589","https://openalex.org/W2889830342","https://openalex.org/W3031636537","https://openalex.org/W2411652523","https://openalex.org/W2967472393","https://openalex.org/W3039654913","https://openalex.org/W2992396845","https://openalex.org/W3213542279","https://openalex.org/W3177148769","https://openalex.org/W2756540778","https://openalex.org/W2894723841","https://openalex.org/W3176616156","https://openalex.org/W2963223306"],"abstract_inverted_index":{"We":[0],"compiled":[1],"a":[2,31,39,49,55,66,94,99,107],"new":[3],"sentence":[4,44,84],"splitting":[5,85],"corpus":[6,79],"that":[7,70,87,105],"is":[8,45,80,114],"composed":[9],"of":[10,13,34,51,57,63,102],"203K":[11],"pairs":[12],"aligned":[14],"complex":[15,95],"source":[16],"and":[17,109,121,124],"simplified":[18],"target":[19],"sentences.":[20],"Contrary":[21],"to":[22,90,116],"previously":[23],"proposed":[24],"text":[25],"simplification":[26],"corpora,":[27],"which":[28,113],"contain":[29],"only":[30],"small":[32],"number":[33],"split":[35],"examples,":[36],"we":[37],"present":[38,106],"dataset":[40],"where":[41],"each":[42,62],"input":[43],"broken":[46],"down":[47],"into":[48,75,98],"set":[50],"minimal":[52,67],"propositions,":[53],"i.e.":[54],"sequence":[56],"sound,":[58],"self-contained":[59],"utterances":[60],"with":[61,93],"them":[64],"presenting":[65],"semantic":[68],"unit":[69],"cannot":[71],"be":[72],"further":[73],"decomposed":[74],"meaningful":[76],"propositions.":[77],"This":[78],"useful":[81],"for":[82,118],"developing":[83],"approaches":[86],"learn":[88],"how":[89],"transform":[91],"sentences":[92,104],"linguistic":[96],"structure":[97,112],"fine-grained":[100],"representation":[101],"short":[103],"simple":[108],"more":[110],"regular":[111],"easier":[115],"process":[117],"downstream":[119],"applications":[120],"thus":[122],"facilitates":[123],"improves":[125],"their":[126],"performance.":[127]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}