{"id":"https://openalex.org/W7144162863","doi":"https://doi.org/10.20736/0002001310","title":"Embedding Tables in Text Context: A New Approach to UFO Tasks","display_name":"Embedding Tables in Text Context: A New Approach to UFO Tasks","publication_year":2023,"publication_date":"2023-12-12","ids":{"openalex":"https://openalex.org/W7144162863","doi":"https://doi.org/10.20736/0002001310"},"language":"en","primary_location":{"id":"pmh:oai:irdb.nii.ac.jp:03100:0005993284","is_oa":true,"landing_page_url":"https://repository.nii.ac.jp/records/2001310","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},"type":"conference-paper","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.nii.ac.jp/records/2001310","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5131369493","display_name":"Hiroyuki Higa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiroyuki Higa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5131131492","display_name":"Yuuki Maeyama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuuki Maeyama","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087059241","display_name":"Keisuke Nanjo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keisuke Nanjo","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.51546392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"none","last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.414900004863739,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.414900004863739,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.38519999384880066,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.053199999034404755,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.7667999863624573},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.76419997215271},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6279000043869019},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.6162999868392944},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4869000017642975},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.39469999074935913}],"concepts":[{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7667999863624573},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.76419997215271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7491999864578247},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6279000043869019},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.6162999868392944},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49070000648498535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48739999532699585},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4869000017642975},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44760000705718994},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.2754000127315521},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26019999384880066},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:irdb.nii.ac.jp:03100:0005993284","is_oa":true,"landing_page_url":"https://repository.nii.ac.jp/records/2001310","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:03100:0005993284","is_oa":true,"landing_page_url":"https://repository.nii.ac.jp/records/2001310","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-Table":[0],"Relationship":[1],"Extraction":[2],"(TTRE)[3]":[3],"has":[4],"emerged":[5],"as":[6],"a":[7,63,66,107,125],"significant":[8],"research":[9],"topic.":[10],"Although":[11],"tables":[12,72,89,119],"enable":[13],"humans":[14],"to":[15,57,78,105],"com-":[16],"prehend":[17],"complex":[18],"data":[19,85,104],"structures":[20],"quickly,":[21],"machines":[22],"often":[23],"struggle":[24],"with":[25,90],"such":[26],"interpretations.":[27],"The":[28],"primary":[29],"challenge":[30],"of":[31,118],"this":[32],"paper":[33],"lies":[34],"in":[35,65,74],"understanding":[36],"the":[37,41,45,79,88,93,102],"myriad":[38],"intentions":[39],"behind":[40],"table\u2019s":[42],"creation":[43],"and":[44,82,97,120],"possible":[46],"ambiguity":[47],"when":[48],"viewed":[49],"without":[50],"context.":[51,68],"We":[52],"pr":[53],"pose":[54],"an":[55],"approach":[56,114],"address":[58],"these":[59],"issues":[60],"by":[61],"embedding":[62],"table":[64],"textual":[67],"Specifically,":[69],"we":[70,100],"convert":[71],"contained":[73],"HTML-":[75],"formatted":[76],"documents":[77],"Markdown":[80],"format":[81],"create":[83],"training":[84,103],"that":[86],"combine":[87],"information":[91],"about":[92],"associated":[94,122],"question":[95],"text":[96],"elements.":[98],"Then,":[99],"use":[101],"train":[106],"QLoRA":[108],"model":[109],"based":[110],"on":[111],"llama2-13b-chat-hf.":[112],"This":[113],"promotes":[115],"holistic":[116],"interpretation":[117],"their":[121],"texts":[123],"within":[124],"single":[126],"vector":[127],"space.":[128]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-04-01T00:00:00"}