{"id":"https://openalex.org/W2740167245","doi":"https://doi.org/10.1145/3077136.3080746","title":"De-duping URLs with Sequence-to-Sequence Neural Networks","display_name":"De-duping URLs with Sequence-to-Sequence Neural Networks","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2740167245","doi":"https://doi.org/10.1145/3077136.3080746","mag":"2740167245"},"language":"en","primary_location":{"id":"doi:10.1145/3077136.3080746","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3077136.3080746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102302135","display_name":"Keyang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keyang Xu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029648803","display_name":"Zhengzhong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengzhong Liu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009879041","display_name":"Jamie Callan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jamie Callan","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.2158,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46549207,"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":"1157","last_page":"1160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9973000288009644,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8161458969116211},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6160591840744019},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.576846718788147},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5203779935836792},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5046151876449585},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44938862323760986},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.44267648458480835},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.442547082901001},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4187897741794586},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4098183214664459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3839726448059082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8161458969116211},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6160591840744019},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.576846718788147},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5203779935836792},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5046151876449585},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44938862323760986},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.44267648458480835},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.442547082901001},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4187897741794586},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4098183214664459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3839726448059082},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3077136.3080746","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3077136.3080746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G1257934570","display_name":"III: Medium: Collaborative Research: Connecting the Ephemeral and Archival Information Networks","funder_award_id":"1160862","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8977677715","display_name":"III: Medium: Selective Search of Large-Scale Text Collections","funder_award_id":"1302206","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W206872386","https://openalex.org/W1924770834","https://openalex.org/W1986968077","https://openalex.org/W2012833704","https://openalex.org/W2013761541","https://openalex.org/W2112104357","https://openalex.org/W2133564696","https://openalex.org/W2134491992","https://openalex.org/W2140018945","https://openalex.org/W2145349611","https://openalex.org/W2949888546","https://openalex.org/W2964165364"],"related_works":["https://openalex.org/W3005260231","https://openalex.org/W2904469652","https://openalex.org/W4362647146","https://openalex.org/W2383572231","https://openalex.org/W2042034567","https://openalex.org/W3179424333","https://openalex.org/W2782340266","https://openalex.org/W4230722125","https://openalex.org/W2149158941","https://openalex.org/W1566984846"],"abstract_inverted_index":{"Many":[0],"URLs":[1,20],"on":[2,58],"the":[3,11,70,96,102],"Internet":[4],"point":[5],"to":[6,42],"identical":[7],"contents,":[8],"which":[9],"increase":[10],"burden":[12],"of":[13,72,74,98],"web":[14,105],"crawlers.":[15,35],"Techniques":[16],"that":[17,79],"detect":[18],"such":[19,29],"(known":[21],"as":[22,30],"URL":[23,54],"de-duping)":[24],"can":[25,68],"greatly":[26],"save":[27],"resources":[28],"bandwidth":[31],"and":[32,86],"storage":[33],"for":[34],"Traditional":[36],"de-duping":[37,55],"methods":[38],"are":[39],"usually":[40],"limited":[41],"heavily":[43],"engineered":[44],"rule":[45],"matching":[46],"strategies.In":[47],"this":[48,99],"work,":[49],"we":[50,94],"propose":[51],"a":[52,80],"novel":[53],"framework":[56,100],"based":[57],"sequence-to-sequence":[59],"(Seq2Seq)":[60],"neural":[61],"networks.":[62],"A":[63],"single":[64],"concise":[65],"translation":[66],"model":[67],"take":[69],"place":[71],"thousands":[73],"explicit":[75],"rules.":[76],"Experiments":[77],"indicate":[78],"vanilla":[81],"Seq2Seq":[82],"architecture":[83],"yields":[84],"robust":[85],"accurate":[87],"results":[88],"in":[89,101],"detecting":[90],"duplicate":[91],"URLs.":[92],"Furthermore,":[93],"demonstrate":[95],"efficiency":[97],"real":[103],"large-scale":[104],"environment.":[106]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}