{"id":"https://openalex.org/W3205396199","doi":null,"title":"SciGen: a Dataset for Reasoning-Aware Text Generation from Scientific Tables","display_name":"SciGen: a Dataset for Reasoning-Aware Text Generation from Scientific Tables","publication_year":2021,"publication_date":"2021-08-20","ids":{"openalex":"https://openalex.org/W3205396199","mag":"3205396199"},"language":"en","primary_location":{"id":"pmh:oai:eprints.whiterose.ac.uk:190593","doi":null,"is_oa":false,"landing_page_url":"https://eprints.whiterose.ac.uk/190593/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},"volume":null,"type":"conference-paper","indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054918343","display_name":"Nafise Sadat Moosavi","orcid":"https://orcid.org/0000-0002-8332-307X","observed_orcids":["https://orcid.org/0000-0002-8332-307X"]},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nafise Sadat Moosavi","raw_affiliation_strings":["Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014688346","display_name":"Andreas R\u00fcckl\u00e9","orcid":"https://orcid.org/0000-0002-4962-0556","observed_orcids":["https://orcid.org/0000-0002-4962-0556"]},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas R\u00fcckl\u00e9","raw_affiliation_strings":["Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4962-0556","affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023802054","display_name":"Dan Roth","orcid":"https://orcid.org/0009-0002-1447-5173","observed_orcids":["https://orcid.org/0009-0002-1447-5173"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Roth","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, United States"],"raw_orcid":"https://orcid.org/0009-0002-1447-5173","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, United States","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027450194","display_name":"Iryna Gurevych","orcid":"https://orcid.org/0000-0003-2187-7621","observed_orcids":["https://orcid.org/0000-0003-2187-7621"]},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Iryna Gurevych","raw_affiliation_strings":["Paderborn University, Paderborn, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2187-7621","affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2706,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.83476541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8140000104904175,"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/T10028","display_name":"Topic Modeling","score":0.8140000104904175,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.14139999449253082,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.015599999576807022,"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/scigen","display_name":"SCIgen","score":0.8429999947547913},{"id":"https://openalex.org/keywords/scientific-tables","display_name":"scientific tables","score":0.7699999809265137},{"id":"https://openalex.org/keywords/data-to-text-generation","display_name":"data-to-text generation","score":0.9190000295639038},{"id":"https://openalex.org/keywords/arithmetic-reasoning","display_name":"arithmetic reasoning","score":0.7599999904632568},{"id":"https://openalex.org/keywords/scientific-articles","display_name":"scientific articles","score":0.3790000081062317},{"id":"https://openalex.org/keywords/expert-annotation","display_name":"expert annotation","score":0.35899999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7120274901390076},{"id":"https://openalex.org/C2992562121","wikidata":"https://www.wikidata.org/wiki/Q3817808","display_name":"Scientific reasoning","level":2,"score":0.508791983127594},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4544915556907654},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4003850519657135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3667186498641968},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3331179618835449},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08870503306388855},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.08310475945472717}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:eprints.whiterose.ac.uk:190593","doi":null,"is_oa":false,"landing_page_url":"https://eprints.whiterose.ac.uk/190593/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:128933","doi":null,"is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/128933/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"},{"id":"mag:3205396199","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=Jul-uX7EV_I","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3156235500","https://openalex.org/W7208754441","https://openalex.org/W7146210530","https://openalex.org/W6958924874","https://openalex.org/W4404787897","https://openalex.org/W4414414612","https://openalex.org/W4404342174","https://openalex.org/W3205136326","https://openalex.org/W4385820399","https://openalex.org/W4366462187"],"abstract_inverted_index":{"We":[0,153],"introduce":[1],"SciGen,":[2,106],"a":[3,138],"new":[4,91],"challenge":[5],"dataset":[6,67],"consisting":[7],"of":[8,20,32,45,74,105,115,118,150,157,198],"tables":[9,26,50,83],"from":[10,84,146],"scientific":[11,25,85,151],"articles":[12],"and":[13,36,55,87,100,164,171,176,188],"their":[14],"corresponding":[15,58,120],"descriptions,":[16,194],"for":[17,93,140],"the":[18,29,33,57,65,70,108,116,119,147,155,166,186,190,196],"task":[19],"reasoning-aware":[21,97],"data-to-text":[22,159],"generation.":[23],"Describing":[24],"goes":[27],"beyond":[28],"surface":[30],"realization":[31],"table":[34,40],"content":[35],"requires":[37],"reasoning":[38,72],"over":[39],"values.":[41],"The":[42,102],"unique":[43],"properties":[44],"SciGen":[46,63,163],"are":[47],"that":[48,68,179],"(1)":[49],"mostly":[51],"contain":[52],"numerical":[53],"values,":[54],"(2)":[56],"descriptions":[59],"require":[60],"arithmetic":[61,71],"reasoning.":[62],"is":[64,111,201],"first":[66],"assesses":[69],"capabilities":[73],"generation":[75,99,160],"models":[76,161,200],"on":[77,162,205],"complex":[78],"input":[79],"structures,":[80],"such":[81],"as":[82],"articles,":[86],"thus":[88],"it":[89],"opens":[90],"avenues":[92],"future":[94],"research":[95],"in":[96,192],"text":[98],"evaluation.":[101,173],"core":[103],"part":[104],"including":[107],"test":[109],"data,":[110],"annotated":[112],"by":[113],"one":[114],"authors":[117],"articles.":[121,152],"Such":[122],"expert":[123],"annotations":[124],"do":[125],"not":[126],"scale":[127],"to":[128],"large":[129],"training":[130,183],"data":[131,184],"sizes.":[132],"To":[133],"tackle":[134],"this,":[135],"we":[136],"propose":[137],"pipeline":[139],"automatically":[141],"extracting":[142],"high-quality":[143,181],"table-description":[144],"pairs":[145],"LaTeX":[148],"sources":[149],"study":[154],"effectiveness":[156],"state-of-the-art":[158,199],"evaluate":[165],"results":[167,175],"using":[168],"common":[169],"metrics":[170],"human":[172],"Our":[174],"analyses":[177],"show":[178],"adding":[180],"unsupervised":[182],"improves":[185],"correctness":[187],"reduces":[189],"hallucination":[191],"generated":[193],"however,":[195],"ability":[197],"still":[202],"severely":[203],"limited":[204],"this":[206],"task.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-10-25T00:00:00"}
