{"id":"https://openalex.org/W2158105359","doi":"https://doi.org/10.1145/2487788.2487922","title":"DFT-extractor","display_name":"DFT-extractor","publication_year":2013,"publication_date":"2013-05-13","ids":{"openalex":"https://openalex.org/W2158105359","doi":"https://doi.org/10.1145/2487788.2487922","mag":"2158105359"},"language":"en","primary_location":{"id":"doi:10.1145/2487788.2487922","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2487788.2487922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on World Wide Web","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/A5070094915","display_name":"Bifan Wei","orcid":"https://orcid.org/0000-0002-9732-3011"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bifan Wei","raw_affiliation_strings":["MOE KLINNS Lab, Xian Jiaotong University, Xian, China"],"affiliations":[{"raw_affiliation_string":"MOE KLINNS Lab, Xian Jiaotong University, Xian, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361891","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-6004-0675"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["MOE KLINNS Lab, Xian Jiaotong University, Xian, China"],"affiliations":[{"raw_affiliation_string":"MOE KLINNS Lab, Xian Jiaotong University, Xian, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034675932","display_name":"Jian Ma","orcid":"https://orcid.org/0000-0002-9269-1130"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Ma","raw_affiliation_strings":["MOE KLINNS Lab, Xian Jiaotong University, Xian, China"],"affiliations":[{"raw_affiliation_string":"MOE KLINNS Lab, Xian Jiaotong University, Xian, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041083459","display_name":"Qinghua Zheng","orcid":"https://orcid.org/0000-0002-8436-4754"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghua Zheng","raw_affiliation_strings":["MOE KLINNS Lab, Xian Jiaotong University, Xian, China"],"affiliations":[{"raw_affiliation_string":"MOE KLINNS Lab, Xian Jiaotong University, Xian, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100691613","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-3942-0593"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Amazon.com Inc, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com Inc, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100778558","display_name":"Boqin Feng","orcid":"https://orcid.org/0000-0002-4879-6090"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boqin Feng","raw_affiliation_strings":["MOE KLINNS Lab, Xian Jiaotong University, Xian, China"],"affiliations":[{"raw_affiliation_string":"MOE KLINNS Lab, Xian Jiaotong University, Xian, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5070094915"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.9618,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83103072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"277","last_page":"280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9911999702453613,"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":0.7813719511032104},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.7623428106307983},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6024654507637024},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5347883105278015},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4824153184890747},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4787815809249878},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.4743807911872864},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4586053788661957},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.43826860189437866},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37009888887405396},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08797919750213623},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.085711270570755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7813719511032104},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.7623428106307983},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6024654507637024},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5347883105278015},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4824153184890747},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4787815809249878},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.4743807911872864},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4586053788661957},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.43826860189437866},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37009888887405396},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08797919750213623},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.085711270570755},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2487788.2487922","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2487788.2487922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W11540594","https://openalex.org/W60048903","https://openalex.org/W105330602","https://openalex.org/W110972138","https://openalex.org/W119864385","https://openalex.org/W1965442176","https://openalex.org/W2047260110","https://openalex.org/W2102153514","https://openalex.org/W2131681506","https://openalex.org/W2132253379","https://openalex.org/W2138605095","https://openalex.org/W2153624566","https://openalex.org/W2165741325","https://openalex.org/W2999011236","https://openalex.org/W3099768174","https://openalex.org/W4247545505"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2793353489"],"abstract_inverted_index":{"Extracting":[0],"faceted":[1,32,74],"taxonomies":[2,33],"from":[3,13,34,44],"the":[4,14,64,97,102],"Web":[5],"has":[6],"received":[7],"increasing":[8],"attention":[9],"in":[10,20,36],"recent":[11],"years":[12],"web":[15],"mining":[16],"community.":[17],"We":[18],"demonstrate":[19],"this":[21],"study":[22],"a":[23,48,56,73,78,83,91],"novel":[24],"system":[25],"called":[26],"DFT-Extractor,":[27],"which":[28],"automatically":[29],"constructs":[30,72],"domain-specific":[31],"Wikipedia":[35,45],"three":[37],"steps:":[38],"1)":[39],"It":[40],"crawls":[41],"domain":[42],"terms":[43],"by":[46,76],"using":[47],"modified":[49],"topical":[50],"crawler.":[51],"2)":[52],"Then":[53],"it":[54,71],"exploits":[55],"classification":[57],"model":[58],"to":[59,95],"extract":[60],"hyponym":[61,99],"relations":[62,100],"with":[63],"use":[65],"of":[66,85,105],"motif-based":[67],"features.":[68],"3)":[69],"Finally,":[70],"taxonomy":[75],"applying":[77],"community":[79],"detection":[80],"algorithm":[81],"and":[82,101],"group":[84],"heuristic":[86],"rules.":[87],"DFT-Extractor":[88],"also":[89],"provides":[90],"graphical":[92],"user":[93],"interface":[94],"visualize":[96],"learned":[98],"tree":[103],"structure":[104],"taxonomies.":[106]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
