{"id":"https://openalex.org/W2604632814","doi":"https://doi.org/10.3233/978-1-61499-484-8-482","title":"A Rule Based DFA Driven Information Extractor for Content Extracting from Web Pages","display_name":"A Rule Based DFA Driven Information Extractor for Content Extracting from Web Pages","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2604632814","doi":"https://doi.org/10.3233/978-1-61499-484-8-482","mag":"2604632814"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-484-8-482","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-484-8-482","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","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/A5100642607","display_name":"Jin Liu","orcid":"https://orcid.org/0000-0001-7249-698X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077440881","display_name":"Chu Danliang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chu Danliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Song Junjie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song Junjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116359727","display_name":"Zhong Bei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong Bei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021716669","display_name":"Cai Biqi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai Biqi","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":0.38686764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"482","last_page":"488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9957000017166138,"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":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.9022353887557983},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6734771728515625},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39438384771347046},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09635823965072632},{"id":"https://openalex.org/keywords/process-engineering","display_name":"Process engineering","score":0.08177289366722107}],"concepts":[{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.9022353887557983},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6734771728515625},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39438384771347046},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09635823965072632},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.08177289366722107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/978-1-61499-484-8-482","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-484-8-482","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"mag:2604632814","is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/intcompsymp/ics2014.html#LiuCSZC14","pdf_url":null,"source":{"id":"https://openalex.org/S4306419857","display_name":"International Conference on Supercomputing","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"International Conference on Supercomputing","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3082848404","https://openalex.org/W1979583797","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2016864125","https://openalex.org/W2358668433","https://openalex.org/W4396701345"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2,18],"tackle":[3],"the":[4,8,22,26,31,67,79,86],"information":[5,12,24,33,42,71],"explosion":[6],"in":[7,85],"Web":[9,41],"era,":[10],"automated":[11],"extraction":[13,34,59],"tools":[14],"are":[15],"urgently":[16],"needed":[17],"help":[19],"people":[20],"find":[21],"useful":[23],"from":[25],"mass.":[27],"This":[28],"paper":[29],"takes":[30],"traditional":[32],"as":[35],"a":[36,40,54],"basis,":[37],"and":[38,82],"propose":[39],"extractor":[43,77],"RDIE(Rule":[44],"based":[45],"DFA":[46],"driven":[47,52],"Information":[48],"Extractor)":[49],"which":[50],"is":[51,63],"by":[53],"DFA(deterministic":[55],"finite":[56],"automata).":[57],"The":[58],"process":[60],"of":[61,69],"RDIE":[62],"elaborate.":[64],"To":[65],"evaluate":[66],"effectiveness":[68],"this":[70],"extractor,":[72],"we":[73],"implemented":[74],"an":[75],"experimental":[76],"with":[78],"proposed":[80],"design":[81],"tested":[83],"it":[84],"shipping":[87],"industry":[88],"domain.":[89]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}