{"id":"https://openalex.org/W2145076056","doi":"https://doi.org/10.1145/1076034.1076079","title":"Title extraction from bodies of HTML documents and its application to web page retrieval","display_name":"Title extraction from bodies of HTML documents and its application to web page retrieval","publication_year":2005,"publication_date":"2005-08-15","ids":{"openalex":"https://openalex.org/W2145076056","doi":"https://doi.org/10.1145/1076034.1076079","mag":"2145076056"},"language":"en","primary_location":{"id":"doi:10.1145/1076034.1076079","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1076034.1076079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5110380262","display_name":"Yunhua Hu","orcid":null},"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":"Yunhua Hu","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055258592","display_name":"Guomao Xin","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guomao Xin","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505570","display_name":"Ruihua Song","orcid":"https://orcid.org/0000-0001-6036-9035"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihua Song","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101922053","display_name":"Guoping Hu","orcid":"https://orcid.org/0000-0002-1276-6201"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoping Hu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China",", University of Science and Technology of China, Hefei, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":", University of Science and Technology of China, Hefei, China#TAB#","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087920747","display_name":"Shuming Shi","orcid":"https://orcid.org/0000-0001-7018-0682"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuming Shi","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China",", University of Science and Technology of China, Hefei, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":", University of Science and Technology of China, Hefei, China#TAB#","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011542448","display_name":"Yunbo Cao","orcid":"https://orcid.org/0009-0005-2558-5206"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbo Cao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China",", University of Science and Technology of China, Hefei, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":", University of Science and Technology of China, Hefei, China#TAB#","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455150","display_name":"Hang Li","orcid":"https://orcid.org/0000-0003-0084-0168"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China",", University of Science and Technology of China, Hefei, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":", University of Science and Technology of China, Hefei, China#TAB#","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.8213,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.98886719,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"250","last_page":"257"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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":0.9639000296592712,"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"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9577999711036682,"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/computer-science","display_name":"Computer science","score":0.836738109588623},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.8068114519119263},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.6742987036705017},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6734691858291626},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5775018930435181},{"id":"https://openalex.org/keywords/font","display_name":"Font","score":0.5070843696594238},{"id":"https://openalex.org/keywords/html","display_name":"HTML","score":0.4301171898841858},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.42913496494293213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26508790254592896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.836738109588623},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.8068114519119263},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.6742987036705017},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6734691858291626},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5775018930435181},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.5070843696594238},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.4301171898841858},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.42913496494293213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26508790254592896},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1076034.1076079","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1076034.1076079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.73.1408","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.73.1408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/users/hangli/HP_files/Hu-etal-SIGIR05.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.86.1021","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.86.1021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/asia/dload_files/group/wsm/SigIR2005/HTML_Title_Extraction.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W10581286","https://openalex.org/W112220366","https://openalex.org/W128350651","https://openalex.org/W179016587","https://openalex.org/W182741375","https://openalex.org/W1230283387","https://openalex.org/W1499023380","https://openalex.org/W1525460779","https://openalex.org/W1559743959","https://openalex.org/W1560151864","https://openalex.org/W1566102133","https://openalex.org/W1594382369","https://openalex.org/W1824331018","https://openalex.org/W1999595522","https://openalex.org/W2015551056","https://openalex.org/W2038124402","https://openalex.org/W2043440779","https://openalex.org/W2083745421","https://openalex.org/W2085030399","https://openalex.org/W2085394232","https://openalex.org/W2104086170","https://openalex.org/W2129595335","https://openalex.org/W2145948275","https://openalex.org/W2153072229","https://openalex.org/W2163915185","https://openalex.org/W2167859982","https://openalex.org/W2598654328","https://openalex.org/W4285719527","https://openalex.org/W6600410643"],"related_works":["https://openalex.org/W4255056669","https://openalex.org/W2019215039","https://openalex.org/W622138672","https://openalex.org/W2913428691","https://openalex.org/W598961908","https://openalex.org/W2508179278","https://openalex.org/W4243796650","https://openalex.org/W2992855911","https://openalex.org/W169337252","https://openalex.org/W1568142529"],"abstract_inverted_index":{"This":[0,50],"paper":[1],"is":[2,36,51,164,180],"concerned":[3],"with":[4],"automatic":[5,40],"extraction":[6,41],"of":[7,12,16,42,47,108,157,171,177,186],"titles":[8,31,43,160,179],"from":[9,44],"the":[10,24,45,75,105,110,132,155,169,175,184],"bodies":[11,46],"HTML":[13,17,30,48,82,145],"documents.":[14,49],"Titles":[15],"documents":[18,146],"should":[19],"be":[20],"correctly":[21],"defined":[22],"in":[23,28,98,112,120,183],"title":[25,99,117,162,172],"fields;":[26],"however,":[27],"reality":[29],"are":[32],"often":[33],"bogus.":[34],"It":[35],"desirable":[37],"to":[38,58,73],"conduct":[39],"an":[52],"issue":[53],"which":[54],"does":[55],"not":[56],"seem":[57],"have":[59],"been":[60],"investigated":[61],"previously.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66,125],"take":[67],"a":[68,79,141],"supervised":[69],"machine":[70],"learning":[71],"approach":[72],"address":[74],"problem.":[76],"We":[77,84,130,139],"propose":[78,140],"specification":[80],"on":[81],"titles.":[83,150],"utilize":[85],"format":[86],"information":[87],"such":[88],"as":[89,96,116],"font":[90,94,114],"size,":[91],"position,":[92],"and":[93,161],"weight":[95],"features":[97],"extraction.":[100],"Our":[101],"method":[102,107,143],"significantly":[103],"outperforms":[104],"baseline":[106],"using":[109,148],"lines":[111],"largest":[113],"size":[115],"(20.9%-32.6%":[118],"improvement":[119],"F1":[121],"score).":[122],"As":[123],"application,":[124],"consider":[126],"web":[127],"page":[128,188],"retrieval.":[129],"use":[131,156,170,176],"TREC":[133],"Web":[134],"Track":[135],"data":[136],"for":[137,144],"evaluation.":[138],"new":[142],"retrieval":[147],"extracted":[149,159,178],"Experimental":[151],"results":[152],"indicate":[153],"that":[154],"both":[158],"fields":[163,173],"almost":[165],"always":[166],"better":[167],"than":[168],"alone;":[174],"particularly":[181],"helpful":[182],"task":[185],"named":[187],"finding":[189],"(23.1%":[190],"-29.0%":[191],"improvements).":[192]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}