{"id":"https://openalex.org/W2060632533","doi":"https://doi.org/10.1109/ase.2011.6100103","title":"Extracting structured data from natural language documents with island parsing","display_name":"Extracting structured data from natural language documents with island parsing","publication_year":2011,"publication_date":"2011-11-01","ids":{"openalex":"https://openalex.org/W2060632533","doi":"https://doi.org/10.1109/ase.2011.6100103","mag":"2060632533"},"language":"en","primary_location":{"id":"doi:10.1109/ase.2011.6100103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ase.2011.6100103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 26th IEEE/ACM International Conference on Automated Software Engineering (ASE 2011)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5082720005","display_name":"Alberto Bacchelli","orcid":"https://orcid.org/0000-0003-0193-6823"},"institutions":[{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Alberto Bacchelli","raw_affiliation_strings":["Faculty of Informatics, University of Lugano, Switzerland","Faculty of Informatics, University of Lugano - Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, University of Lugano, Switzerland","institution_ids":["https://openalex.org/I57201433"]},{"raw_affiliation_string":"Faculty of Informatics, University of Lugano - Switzerland","institution_ids":["https://openalex.org/I57201433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070165042","display_name":"Anthony Cleve","orcid":null},"institutions":[{"id":"https://openalex.org/I149768937","display_name":"University of Namur","ror":"https://ror.org/03d1maw17","country_code":"BE","type":"education","lineage":["https://openalex.org/I149768937"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Anthony Cleve","raw_affiliation_strings":["Faculty of Informatics, University of Namur, Belgium","Faculty of Informatics, University of Namur, Belgium#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, University of Namur, Belgium","institution_ids":["https://openalex.org/I149768937"]},{"raw_affiliation_string":"Faculty of Informatics, University of Namur, Belgium#TAB#","institution_ids":["https://openalex.org/I149768937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038257395","display_name":"Michele Lanza","orcid":"https://orcid.org/0000-0003-4391-0197"},"institutions":[{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Michele Lanza","raw_affiliation_strings":["Faculty of Informatics, University of Lugano, Switzerland","Faculty of Informatics, University of Lugano - Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, University of Lugano, Switzerland","institution_ids":["https://openalex.org/I57201433"]},{"raw_affiliation_string":"Faculty of Informatics, University of Lugano - Switzerland","institution_ids":["https://openalex.org/I57201433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084194284","display_name":"Andrea Mocci","orcid":"https://orcid.org/0000-0002-8426-5676"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Mocci","raw_affiliation_strings":["DEI, Politecnico di Milano, Italy","DEI Politecnico di Milano - Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DEI, Politecnico di Milano, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"DEI Politecnico di Milano - Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.1131,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.96031333,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"476","last_page":"479"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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/T10260","display_name":"Software Engineering Research","score":0.9988999962806702,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9932000041007996,"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":0.8555124998092651},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.8152621984481812},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.7567183375358582},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5921611189842224},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5787532329559326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5311333537101746},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4944150447845459},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4907287359237671},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.46379974484443665},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4221358597278595},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36414891481399536},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2774689793586731},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11744216084480286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8555124998092651},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8152621984481812},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.7567183375358582},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5921611189842224},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5787532329559326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5311333537101746},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4944150447845459},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4907287359237671},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.46379974484443665},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4221358597278595},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36414891481399536},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2774689793586731},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11744216084480286},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ase.2011.6100103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ase.2011.6100103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 26th IEEE/ACM International Conference on Automated Software Engineering (ASE 2011)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.unamur.be:openaire_cris_publications/0a9c9317-4a81-4be0-bb99-d2bfd7fbb4a4","is_oa":false,"landing_page_url":"https://researchportal.unamur.be/en/publications/0a9c9317-4a81-4be0-bb99-d2bfd7fbb4a4","pdf_url":null,"source":{"id":"https://openalex.org/S4406922457","display_name":"Repository of the University of Namur","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bacchelli, A, Cleve, A, Lanza, M & Mocci, A 2011, Extracting Structured Data from Natural Language Documents with Island Parsing. in P Alexer, S Corina, P John & G Hosking (eds), Proceedings of the 26th International Conference on Automated Software Engineering (ASE 2011). IEEE Computer Society Press, pp. 476-479.","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:re.public.polimi.it:11311/769276","is_oa":false,"landing_page_url":"http://hdl.handle.net/11311/769276","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8600000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1850047186","https://openalex.org/W2013399578","https://openalex.org/W2025599150","https://openalex.org/W2056351581","https://openalex.org/W2109932952","https://openalex.org/W2127340092","https://openalex.org/W3158497763","https://openalex.org/W4255936169"],"related_works":["https://openalex.org/W2358294942","https://openalex.org/W3157284875","https://openalex.org/W2259406085","https://openalex.org/W2099715052","https://openalex.org/W2147241511","https://openalex.org/W4226247999","https://openalex.org/W4213176082","https://openalex.org/W2187398150","https://openalex.org/W3209772662","https://openalex.org/W2293063786"],"abstract_inverted_index":{"The":[0],"design":[1,53],"and":[2,49,54,59,87,131],"evolution":[3],"of":[4,13,45,62,91],"a":[5,42,51,65],"software":[6,113],"system":[7],"leave":[8],"traces":[9],"in":[10,26,32,68,96],"various":[11],"kinds":[12],"artifacts.":[14,99],"In":[15],"software,":[16],"produced":[17],"by":[18,29,104],"humans":[19],"for":[20,47],"humans,":[21],"many":[22],"artifacts":[23],"are":[24],"written":[25],"natural":[27,76,97],"language":[28,77,98],"people":[30],"involved":[31],"the":[33,57,89],"project.":[34],"Such":[35],"entities":[36],"contain":[37],"structured":[38,92,124],"information":[39,93],"which":[40,72],"constitute":[41],"valuable":[43],"source":[44],"knowledge":[46],"analyzing":[48],"comprehending":[50],"system's":[52],"evolution.":[55],"However,":[56],"ambiguous":[58],"informal":[60],"nature":[61],"narrative":[63],"is":[64,73],"serious":[66],"challenge":[67],"gathering":[69],"such":[70],"information,":[71],"scattered":[74],"throughout":[75],"text.":[78],"We":[79,100,115],"present":[80],"an":[81],"approach-based":[82],"on":[83],"island":[84],"parsing-to":[85],"recognize":[86],"enable":[88],"parsing":[90],"that":[94,117],"occur":[95],"evaluate":[101],"our":[102],"approach":[103,119],"applying":[105],"it":[106],"to":[107,111,122],"mailing":[108],"lists":[109],"pertaining":[110],"three":[112],"systems.":[114],"show":[116],"this":[118],"allows":[120],"us":[121],"extract":[123],"data":[125],"from":[126],"emails":[127],"with":[128],"high":[129],"precision":[130],"recall.":[132]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
