{"id":"https://openalex.org/W2250433529","doi":"https://doi.org/10.3115/v1/w14-0403","title":"Less Destructive Cleaning of Web Documents by Using Standoff Annotation","display_name":"Less Destructive Cleaning of Web Documents by Using Standoff Annotation","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2250433529","doi":"https://doi.org/10.3115/v1/w14-0403","mag":"2250433529"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-0403","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0403","pdf_url":"https://aclanthology.org/W14-0403.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":"Proceedings of the 9th Web as Corpus Workshop (WaC-9)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-0403.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001900334","display_name":"Maik St\u00fchrenberg","orcid":"https://orcid.org/0000-0002-5303-5392"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Maik St\u00fchrenberg","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5001900334"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.819,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84248671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"16","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9965999722480774,"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":0.9965999722480774,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9922999739646912,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9697999954223633,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.826888382434845},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.8158203363418579},{"id":"https://openalex.org/keywords/serialization","display_name":"Serialization","score":0.8124918937683105},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.6842166185379028},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6721780896186829},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6405372619628906},{"id":"https://openalex.org/keywords/html","display_name":"HTML","score":0.4549252390861511},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4367252588272095},{"id":"https://openalex.org/keywords/web-standards","display_name":"Web standards","score":0.41065263748168945},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.2054017186164856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10141444206237793},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09120738506317139}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.826888382434845},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8158203363418579},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.8124918937683105},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.6842166185379028},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6721780896186829},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6405372619628906},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.4549252390861511},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4367252588272095},{"id":"https://openalex.org/C182321512","wikidata":"https://www.wikidata.org/wiki/Q1153289","display_name":"Web standards","level":3,"score":0.41065263748168945},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.2054017186164856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10141444206237793},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09120738506317139}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/w14-0403","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0403","pdf_url":"https://aclanthology.org/W14-0403.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":"Proceedings of the 9th Web as Corpus Workshop (WaC-9)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.675.4581","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.675.4581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://anthology.aclweb.org/W/W14/W14-0403.pdf","raw_type":"text"},{"id":"pmh:oai:pub.uni-bielefeld.de:2941369","is_oa":false,"landing_page_url":"https://pub.uni-bielefeld.de/record/2941369","pdf_url":null,"source":{"id":"https://openalex.org/S4306401670","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-0403","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0403","pdf_url":"https://aclanthology.org/W14-0403.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":"Proceedings of the 9th Web as Corpus Workshop (WaC-9)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250433529.pdf","grobid_xml":"https://content.openalex.org/works/W2250433529.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W56186637","https://openalex.org/W121228829","https://openalex.org/W132843624","https://openalex.org/W155517163","https://openalex.org/W160790211","https://openalex.org/W1561402931","https://openalex.org/W1965014786","https://openalex.org/W2400962361","https://openalex.org/W2417057507","https://openalex.org/W2476037704","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4205488131","https://openalex.org/W4206048862","https://openalex.org/W4205700492","https://openalex.org/W2042562985","https://openalex.org/W183683573","https://openalex.org/W3021385460","https://openalex.org/W2139931245","https://openalex.org/W1990889981","https://openalex.org/W1566994962","https://openalex.org/W2028157995"],"abstract_inverted_index":{"Standoff":[0],"annotation,":[1],"that":[2,40],"is,":[3],"the":[4,25,60],"separa-tion":[5],"of":[6,27,59],"primary":[7],"data":[8],"and":[9,57],"markup,":[10],"can":[11],"be":[12],"an":[13],"interesting":[14],"option":[15],"to":[16],"annotate":[17],"web":[18,32,45],"pages":[19,46],"since":[20],"it":[21],"does":[22],"not":[23],"demand":[24],"re-moval":[26],"annotations":[28],"already":[29],"present":[30,36],"in":[31,51],"pages.":[33],"We":[34],"will":[35],"a":[37,52],"standoff":[38],"se-rialization":[39],"allows":[41],"for":[42],"annotating":[43],"well-formed":[44],"with":[47],"multiple":[48],"annota-tion":[49],"layers":[50],"single":[53],"instance,":[54],"easing":[55],"pro-cessing":[56],"analyzing":[58],"data.":[61],"1":[62]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
