{"id":"https://openalex.org/W3143951786","doi":"https://doi.org/10.1109/wiiatw.2007.4427643","title":"An Intelligent Web Agent to Mine Bilingual Parallel Pages via Automatic Discovery of URL Pairing Patterns","display_name":"An Intelligent Web Agent to Mine Bilingual Parallel Pages via Automatic Discovery of URL Pairing Patterns","publication_year":2007,"publication_date":"2007-11-01","ids":{"openalex":"https://openalex.org/W3143951786","doi":"https://doi.org/10.1109/wiiatw.2007.4427643","mag":"3143951786"},"language":"en","primary_location":{"id":"doi:10.1109/wiiatw.2007.4427643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wiiatw.2007.4427643","pdf_url":null,"source":{"id":"https://openalex.org/S4363606436","display_name":"2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Workshops","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Workshops","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/A5069506463","display_name":"Chunyu Kit","orcid":"https://orcid.org/0000-0002-6445-7400"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chunyu Kit","raw_affiliation_strings":["Department of Chinese, Translation and Linguistics, City University of Hong Kong, Kowloon, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chinese, Translation and Linguistics, City University of Hong Kong, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069233950","display_name":"Jessica Yee Ha Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jessica Yee Ha Ng","raw_affiliation_strings":["Department of Chinese, Translation and Linguistics, City University of Hong Kong, Kowloon, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chinese, Translation and Linguistics, City University of Hong Kong, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.47811218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9926999807357788,"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":0.9926999807357788,"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":0.9850000143051147,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9832000136375427,"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":0.8221508264541626},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7414939403533936},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.685828447341919},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6308883428573608},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49796271324157715},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4660685360431671},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46408841013908386},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.44497597217559814},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4414416253566742},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20172396302223206},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.19312763214111328},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07210913300514221}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8221508264541626},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7414939403533936},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.685828447341919},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6308883428573608},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49796271324157715},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4660685360431671},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46408841013908386},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.44497597217559814},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4414416253566742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20172396302223206},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.19312763214111328},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07210913300514221},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wiiatw.2007.4427643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wiiatw.2007.4427643","pdf_url":null,"source":{"id":"https://openalex.org/S4363606436","display_name":"2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Workshops","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Workshops","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1979144454","https://openalex.org/W4239898202","https://openalex.org/W2069679074","https://openalex.org/W2115253914","https://openalex.org/W3116613346","https://openalex.org/W4237456423","https://openalex.org/W2911454453","https://openalex.org/W2055154498","https://openalex.org/W2316185946","https://openalex.org/W2376574812"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3,118],"intelligent":[4],"agent":[5],"to":[6,113,137],"facilitate":[7],"bi-text":[8],"mining":[9],"from":[10],"the":[11,35,47,51,54,62,107],"Web":[12,25,66,72,97,126],"via":[13],"automatic":[14],"discovery":[15],"of":[16,30,37,57,65,96],"URL":[17,38],"pairing":[18,132],"patterns":[19,133],"(or":[20],"keys)":[21],"for":[22,50,53,90],"retrieving":[23],"parallel":[24,125],"pages.":[26],"The":[27],"linking":[28],"power":[29],"a":[31,70,110],"key,":[32],"defined":[33],"as":[34,46,83],"number":[36,64],"pairs":[39,68],"that":[40,59,102,134],"it":[41],"can":[42,60,121],"match,":[43],"is":[44],"used":[45],"objective":[48],"function":[49],"search":[52,112],"best":[55],"set":[56],"keys":[58],"find":[61],"greatest":[63],"page":[67,98],"within":[69],"bilingual":[71],"site.":[73],"Our":[74],"experiments":[75],"show":[76],"that,":[77],"with":[78,117],"no":[79,87,93],"prior":[80],"knowledge":[81],"such":[82],"ad":[84],"hoc":[85],"heuristics,":[86],"labelled":[88],"data":[89],"training":[91],"and":[92,100,128],"similarity":[94],"analysis":[95],"structure":[99],"content":[101],"are":[103,135],"commonly":[104],"involved":[105],"in":[106],"existing":[108],"approaches,":[109],"best-first":[111],"approximate":[114],"this":[115],"optimization":[116],"empirical":[119],"threshold":[120],"recognize":[122],"98.1%":[123],"true":[124],"pages":[127],"discover":[129],"many":[130],"irregular":[131],"unlikely":[136],"be":[138],"discovered":[139],"by":[140],"other":[141],"approaches.":[142]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
