{"id":"https://openalex.org/W4412944500","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1364","title":"NBDESCRIB: A Dataset for Text Description Generation from Tables and Code in Jupyter Notebooks with Guidelines","display_name":"NBDESCRIB: A Dataset for Text Description Generation from Tables and Code in Jupyter Notebooks with Guidelines","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944500","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1364"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1364","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1364","pdf_url":"https://aclanthology.org/2025.findings-acl.1364.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1364.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012411636","display_name":"Xuye Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuye Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041146184","display_name":"Tengfei Ma","orcid":"https://orcid.org/0000-0003-1426-1060"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tengfei Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008792199","display_name":"Yimu Wang","orcid":"https://orcid.org/0000-0003-4255-9104"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yimu Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027441066","display_name":"Fengjie Wang","orcid":"https://orcid.org/0000-0002-3267-9324"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fengjie Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5061636756","display_name":"Jian Zhao","orcid":"https://orcid.org/0000-0002-0619-7866"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":"26584","last_page":"26606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9959999918937683,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9959999918937683,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9830999970436096,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9391999840736389,"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/computer-science","display_name":"Computer science","score":0.7360329627990723},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5296218991279602},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.48270249366760254},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3835042119026184},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3829449713230133},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3791496157646179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360329627990723},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5296218991279602},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.48270249366760254},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3835042119026184},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3829449713230133},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3791496157646179},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1364","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1364","pdf_url":"https://aclanthology.org/2025.findings-acl.1364.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1364","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1364","pdf_url":"https://aclanthology.org/2025.findings-acl.1364.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2380475602","display_name":null,"funder_award_id":"03966","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G3525686075","display_name":null,"funder_award_id":"RGPIN-2020","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G8797334686","display_name":null,"funder_award_id":"2020-03966","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944500.pdf","grobid_xml":"https://content.openalex.org/works/W4412944500.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4231937131","https://openalex.org/W323219885","https://openalex.org/W2063928587","https://openalex.org/W1487966966","https://openalex.org/W1589342014","https://openalex.org/W1480341462","https://openalex.org/W598950423","https://openalex.org/W4256673449","https://openalex.org/W4292559016","https://openalex.org/W2143331802"],"abstract_inverted_index":{"Generating":[0],"cell-level":[1],"descriptions":[2,32,43,105,132],"for":[3,25],"Jupyter":[4,26,81],"Notebooks,":[5],"which":[6],"is":[7],"a":[8,68,91],"major":[9],"resource":[10],"consisting":[11],"of":[12,114,174],"codes,":[13],"tables,":[14,76,97],"and":[15,77,89,98,103,122,143,161,178,191],"descriptions,":[16,124],"has":[17],"been":[18],"attracting":[19],"increasing":[20],"research":[21],"attention.However,":[22],"existing":[23,112],"methods":[24],"Notebooks":[27],"mostly":[28],"focus":[29],"on":[30],"generating":[31],"from":[33],"code":[34,176],"snippets":[35],"or":[36],"table":[37],"outputs":[38],"independently.On":[39],"the":[40,137,153],"other":[41],"side,":[42],"should":[44],"be":[45],"personalized":[46,71,104],"as":[47,101,106],"users":[48],"have":[49],"different":[50,53],"purposes":[51],"in":[52,80,140,149,158],"scenarios":[54],"while":[55,111,152],"previous":[56],"work":[57],"ignored":[58],"this":[59,64,84],"situation":[60],"during":[61],"description":[62,72],"generation.In":[63],"work,":[65],"we":[66,87],"formulate":[67],"new":[69,85],"task,":[70,86],"generation":[73,116],"with":[74,168],"code,":[75,96],"user-written":[78,99,134],"guidelines":[79,100,186],"Notebooks.To":[82],"evaluate":[83],"collect":[88],"propose":[90],"benchmark,":[92],"namely":[93],"NBDESCRIB,":[94],"containing":[95],"inputs":[102],"targets.Extensive":[107],"experiments":[108],"show":[109,183],"that":[110,184],"models":[113,148],"text":[115],"are":[117],"able":[118],"to":[119,128],"generate":[120],"fluent":[121],"readable":[123],"they":[125],"still":[126],"struggle":[127],"produce":[129],"factually":[130],"correct":[131],"without":[133],"guidelines.CodeT5":[135],"achieved":[136],"highest":[138],"scores":[139],"Orientation":[141,159],"(1.27)":[142],"Correctness":[144,162],"(-0.43)":[145],"among":[146],"foundation":[147],"human":[150],"evaluation,":[151],"ground":[154],"truth":[155],"scored":[156],"higher":[157],"(1.45)":[160],"(1.19).Common":[163],"error":[164],"patterns":[165],"involve":[166],"misalignment":[167],"guidelines,":[169],"incorrect":[170],"variable":[171],"values,":[172],"omission":[173],"important":[175],"information,":[177],"reasoning":[179],"errors.Moreover,":[180],"ablation":[181],"studies":[182],"adding":[185],"significantly":[187],"enhances":[188],"performance.both":[189],"qualitatively":[190],"quantitatively.Table":[192],"passengerid":[193],"pclass":[194],"sex":[195],"age":[196],"fare":[197],"cabin":[198],"embarked":[199],"y_pred":[200],"y_scores":[201],"0":[202],"892":[203],"3":[204],"male":[205],"34.5":[206],"7.":[207]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}