{"id":"https://openalex.org/W4409403749","doi":"https://doi.org/10.1145/3711542.3711576","title":"From Unstructured Documents to Annotated Information: An Optimized Pipeline to Process Industrial Requirements","display_name":"From Unstructured Documents to Annotated Information: An Optimized Pipeline to Process Industrial Requirements","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W4409403749","doi":"https://doi.org/10.1145/3711542.3711576"},"language":"en","primary_location":{"id":"doi:10.1145/3711542.3711576","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711542.3711576","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711542.3711576","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711542.3711576","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117130433","display_name":"Nocente Arianna","orcid":"https://orcid.org/0009-0001-6138-5720"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Nocente Arianna","raw_affiliation_strings":["Department of Information Engineering, University of Pisa, Pisa, Italy and Alstom Ferroviaria Spa, Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Pisa, Pisa, Italy and Alstom Ferroviaria Spa, Bologna, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117130434","display_name":"Risi Riccardo","orcid":"https://orcid.org/0009-0000-0622-4564"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Risi Riccardo","raw_affiliation_strings":["Marketing Division, Columbia Business School, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Marketing Division, Columbia Business School, New York, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065996977","display_name":"Gabriele Pannocchia","orcid":"https://orcid.org/0000-0002-5578-344X"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pannocchia Gabriele","raw_affiliation_strings":["Department of Civil and Industrial Engineering, University of Pisa, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Civil and Industrial Engineering, University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002595735","display_name":"Giulio Rossetti","orcid":"https://orcid.org/0000-0003-3373-1240"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Rossetti Giulio","raw_affiliation_strings":["Institute of Science and Technologies, Italian National Research Council (CNR), Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Institute of Science and Technologies, Italian National Research Council (CNR), Pisa, Italy","institution_ids":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5117130433"],"corresponding_institution_ids":["https://openalex.org/I108290504"],"apc_list":null,"apc_paid":null,"fwci":0.7794,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83378562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"272","last_page":"278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9939000010490417,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9939000010490417,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9793000221252441,"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.9692999720573425,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7198512554168701},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6509935259819031},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6138473153114319},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49438953399658203},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34305626153945923},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18454065918922424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7198512554168701},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6509935259819031},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6138473153114319},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49438953399658203},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34305626153945923},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18454065918922424}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3711542.3711576","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711542.3711576","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711542.3711576","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arpi.unipi.it:11568/1321687","is_oa":false,"landing_page_url":"https://hdl.handle.net/11568/1321687","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"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":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dnet:iris________::981217caa33e335c48f7174058651acf","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference article"}],"best_oa_location":{"id":"doi:10.1145/3711542.3711576","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711542.3711576","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711542.3711576","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409403749.pdf","grobid_xml":"https://content.openalex.org/works/W4409403749.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W8759066","https://openalex.org/W2004147962","https://openalex.org/W2060736388","https://openalex.org/W2127626360","https://openalex.org/W2148996482","https://openalex.org/W2157856440","https://openalex.org/W2164863177","https://openalex.org/W2333183372","https://openalex.org/W2617548478","https://openalex.org/W2758253540","https://openalex.org/W2760476066","https://openalex.org/W2911964244","https://openalex.org/W2999060535","https://openalex.org/W3023211159","https://openalex.org/W3143230942","https://openalex.org/W3153389197","https://openalex.org/W4206254927","https://openalex.org/W4251641598","https://openalex.org/W4281743154","https://openalex.org/W4324054705","https://openalex.org/W4362513403","https://openalex.org/W4393759182"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Managing":[0],"bid":[1,58],"documentation":[2],"in":[3,15,87,110,179],"large,":[4],"evolving":[5],"technology":[6],"companies":[7],"is":[8,49,95,136,172,192,206],"inherently":[9],"complex,":[10],"often":[11],"due":[12],"to":[13,54,60,66,102,124,183,215,233],"inconsistencies":[14],"information":[16,72],"such":[17],"as":[18],"translations,":[19],"file":[20],"updates,":[21],"and":[22,36,62,65,84,90,97,119,153,158,161,235],"manual":[23],"data":[24,99,126],"extraction.These":[25],"processes":[26],"involve":[27],"multiple":[28],"departments,":[29],"including":[30],"software,":[31],"hardware,":[32],"products,":[33],"infrastructure,":[34],"materials,":[35],"regulations,":[37],"requiring":[38],"collaboration":[39],"across":[40],"geographically":[41],"distributed":[42,231],"teams":[43],"with":[44,82],"different":[45],"native":[46],"languages.This":[47],"complexity":[48],"exacerbated":[50],"by":[51],"the":[52,103,185,216,222],"need":[53],"trace":[55],"requirements":[56],"from":[57,74],"offers":[59],"code":[61],"product":[63],"development,":[64],"perform":[67],"similarity":[68],"analysis":[69],"when":[70],"needed.Unstructured":[71],"comes":[73],"diverse":[75],"sources":[76],"like":[77],"scans":[78],"and/or":[79],"editable":[80],"texts":[81],"tables":[83],"images,":[85],"written":[86],"various":[88],"languages":[89],"using":[91,174,200],"domain-specific":[92],"terminology.Manual":[93],"processing":[94],"error-prone,":[96],"translating":[98],"can":[100],"lead":[101],"loss":[104],"of":[105,144,197,224],"context-specific":[106],"meanings":[107],"or":[108,129],"issues":[109],"safety-critical":[111],"domains.This":[112],"study":[113,178,191],"combines":[114],"Natural":[115],"Language":[116],"Processing":[117],"(NLP)":[118],"Optical":[120],"Character":[121],"Recognition":[122],"(OCR)":[123],"classify":[125],"into":[127],"\"information\"":[128],"\"requirement\"":[130],"while":[131],"preserving":[132],"multilingualism.A":[133],"dual-pipeline":[134],"approach":[135],"developed,":[137],"featuring":[138],"both":[139],"a":[140,162,175,188,207,225],"meta-classifier":[141],"(an":[142],"ensemble":[143],"Logistic":[145],"Regression,":[146],"Support":[147],"Vector":[148],"Machine,":[149],"Multinomial":[150],"Naive":[151],"Bayes,":[152],"Random":[154],"Forest)":[155],"for":[156,165],"robust":[157],"interpretable":[159],"results,":[160],"BERT":[163],"model":[164],"capturing":[166],"subtle":[167],"linguistic":[168],"patterns.The":[169],"proposed":[170],"pipeline":[171],"validated":[173],"real-world":[176],"case":[177,190],"railway":[180],"requirement":[181],"annotation.Additionally,":[182],"demonstrate":[184],"methodology's":[186],"flexibility,":[187],"second":[189],"conducted":[193],"on":[194],"topic":[195],"classification":[196],"newspaper":[198],"articles":[199],"publicly":[201],"accessible":[202],"data.The":[203],"pipeline's":[204],"output":[205],"software":[208],"solution":[209],"that":[210],"uses":[211],"pre-trained":[212],"models":[213],"tailored":[214],"respective":[217],"domains.Future":[218],"developments":[219],"will":[220],"include":[221],"creation":[223],"graphical":[226],"user":[227],"interface":[228],"(GUI),":[229],"enabling":[230],"users":[232],"easily":[234],"efficiently":[236],"search,":[237],"update":[238],"their":[239]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}