{"id":"https://openalex.org/W2059380771","doi":"https://doi.org/10.1145/1410140.1410182","title":"Identifying and expanding titles in web texts","display_name":"Identifying and expanding titles in web texts","publication_year":2008,"publication_date":"2008-09-16","ids":{"openalex":"https://openalex.org/W2059380771","doi":"https://doi.org/10.1145/1410140.1410182","mag":"2059380771"},"language":"en","primary_location":{"id":"doi:10.1145/1410140.1410182","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1410140.1410182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eighth ACM symposium on Document engineering","raw_type":"proceedings-article"},"type":"preprint","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/A5103370557","display_name":"Cl\u00e9mentine Adam","orcid":null},"institutions":[{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Cl\u00e9mentine Adam","raw_affiliation_strings":["IRIT-UPS, Toulouse, France"],"affiliations":[{"raw_affiliation_string":"IRIT-UPS, Toulouse, France","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I134560555"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091143083","display_name":"Estelle Delpech","orcid":null},"institutions":[{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Estelle Delpech","raw_affiliation_strings":["IRIT-UPS, Toulouse, France"],"affiliations":[{"raw_affiliation_string":"IRIT-UPS, Toulouse, France","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I134560555"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112073332","display_name":"Patrick Saint\u2010Dizier","orcid":null},"institutions":[{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I3131550300","display_name":"Universit\u00e9 Toulouse-I-Capitole","ror":"https://ror.org/0443n9e75","country_code":"FR","type":"education","lineage":["https://openalex.org/I3131550300"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Patrick Saint-Dizier","raw_affiliation_strings":["IRIT-CNRS, Toulouse, France","IRIT-CNRS, Toulouse - France#TAB#"],"affiliations":[{"raw_affiliation_string":"IRIT-CNRS, Toulouse, France","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I134560555","https://openalex.org/I3131550300","https://openalex.org/I4210160189","https://openalex.org/I4210152422","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"IRIT-CNRS, Toulouse - France#TAB#","institution_ids":["https://openalex.org/I4210152422","https://openalex.org/I1294671590","https://openalex.org/I134560555","https://openalex.org/I4210119061","https://openalex.org/I3131550300","https://openalex.org/I4210160189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103370557"],"corresponding_institution_ids":["https://openalex.org/I134560555","https://openalex.org/I4210119061"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.07829457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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/T13629","display_name":"Text Readability and Simplification","score":0.998199999332428,"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":0.8576960563659668},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.7430709600448608},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6628115773200989},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6515666246414185},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6514871716499329},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6393550634384155},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5307618975639343},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5239075422286987},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4623265266418457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32208147644996643},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.06361117959022522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8576960563659668},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7430709600448608},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6628115773200989},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6515666246414185},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6514871716499329},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6393550634384155},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5307618975639343},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5239075422286987},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4623265266418457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32208147644996643},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.06361117959022522},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1410140.1410182","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1410140.1410182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eighth ACM symposium on Document engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W55112844","https://openalex.org/W1828401780","https://openalex.org/W2053089403","https://openalex.org/W2169503695","https://openalex.org/W2692133141","https://openalex.org/W4251900293"],"related_works":["https://openalex.org/W2012531322","https://openalex.org/W2402761219","https://openalex.org/W2785900585","https://openalex.org/W2353730437","https://openalex.org/W2490303674","https://openalex.org/W2609066826","https://openalex.org/W2810752900","https://openalex.org/W2365677836","https://openalex.org/W2531295127","https://openalex.org/W1565952126"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,54],"present":[4],"an":[5],"analysis":[6],"based":[7],"on":[8,27],"linguistic":[9],"and":[10],"typographic":[11],"features":[12],"that":[13,68],"allows":[14],"for":[15],"the":[16,61],"identification":[17],"of":[18,38,46,52],"titles":[19,31,47,69],"in":[20,25,64],"web":[21],"documents.":[22],"We":[23],"focus":[24],"particular":[26,65],"procedural":[28],"texts.":[29],"Identifying":[30],"is":[32],"a":[33,57],"difficult":[34],"task":[35],"because":[36,51],"ways":[37],"encoding":[39],"them":[40],"are":[41,48,70],"very":[42],"diverse.":[43],"A":[44],"number":[45],"also":[49],"incomplete":[50],"context,":[53],"propose":[55],"therefore":[56],"way":[58],"to":[59],"retrieve":[60],"missing":[62],"elements,":[63],"predicates,":[66],"so":[67],"fully":[71],"intelligible.":[72]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
