{"id":"https://openalex.org/W2250855669","doi":"https://doi.org/10.18653/v1/w13-5007","title":"Understanding seed selection in bootstrapping","display_name":"Understanding seed selection in bootstrapping","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2250855669","doi":"https://doi.org/10.18653/v1/w13-5007","mag":"2250855669"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w13-5007","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w13-5007","pdf_url":"https://aclanthology.org/W13-5007.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of TextGraphs-8 Graph-based Methods for Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W13-5007.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007171156","display_name":"Yo Ehara","orcid":"https://orcid.org/0000-0001-9314-4617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yo Ehara","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060421432","display_name":"Issei Sato","orcid":"https://orcid.org/0000-0002-5066-1435"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Issei Sato","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042638926","display_name":"Hidekazu Oiwa","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hidekazu Oiwa","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020912760","display_name":"Hiroshi Nakagawa","orcid":"https://orcid.org/0000-0002-3024-9136"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Nakagawa","raw_affiliation_strings":["Univ.\\ of Tokyo"],"affiliations":[{"raw_affiliation_string":"Univ.\\ of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007171156"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.9954,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.83944359,"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":"44","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9973000288009644,"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/bootstrapping","display_name":"Bootstrapping (finance)","score":0.9552570581436157},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6864123344421387},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5751184821128845},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.568743109703064},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5067041516304016},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49916911125183105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49542224407196045},{"id":"https://openalex.org/keywords/mean-reciprocal-rank","display_name":"Mean reciprocal rank","score":0.438870906829834},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.43169134855270386},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3410203456878662},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2188190221786499},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.07815113663673401}],"concepts":[{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.9552570581436157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6864123344421387},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5751184821128845},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.568743109703064},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5067041516304016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49916911125183105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49542224407196045},{"id":"https://openalex.org/C44083865","wikidata":"https://www.wikidata.org/wiki/Q3853443","display_name":"Mean reciprocal rank","level":2,"score":0.438870906829834},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.43169134855270386},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3410203456878662},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2188190221786499},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.07815113663673401},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w13-5007","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w13-5007","pdf_url":"https://aclanthology.org/W13-5007.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of TextGraphs-8 Graph-based Methods for Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w13-5007","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w13-5007","pdf_url":"https://aclanthology.org/W13-5007.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of TextGraphs-8 Graph-based Methods for Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250855669.pdf","grobid_xml":"https://content.openalex.org/works/W2250855669.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1514969207","https://openalex.org/W1845402413","https://openalex.org/W1980018014","https://openalex.org/W2034291858","https://openalex.org/W2068737686","https://openalex.org/W2101210369","https://openalex.org/W2103137496","https://openalex.org/W2137023796","https://openalex.org/W2138288827","https://openalex.org/W2152005244","https://openalex.org/W2882319491","https://openalex.org/W2914331073"],"related_works":["https://openalex.org/W2025252807","https://openalex.org/W4297883370","https://openalex.org/W2980701895","https://openalex.org/W3118323771","https://openalex.org/W2096699795","https://openalex.org/W2111227719","https://openalex.org/W1923577452","https://openalex.org/W1974228362","https://openalex.org/W2360353848","https://openalex.org/W2884580467"],"abstract_inverted_index":{"Bootstrapping":[0],"has":[1,66],"recently":[2],"become":[3],"the":[4,24,62,67,74,78,92],"focus":[5],"of":[6,70,84],"much":[7],"attention":[8],"in":[9,77,88],"natural":[10],"language":[11],"processing":[12],"to":[13,36,54],"reduce":[14,55],"labeling":[15,57],"cost.In":[16],"bootstrapping,":[17],"unlabeled":[18,63,75],"instances":[19],"can":[20,120],"be":[21],"harvested":[22],"from":[23],"initial":[25],"labeled":[26],"\"seed\"":[27],"set.The":[28],"selected":[29],"seed":[30,40,79,122,141],"set":[31,41],"affects":[32],"accuracy,":[33],"but":[34],"how":[35],"select":[37,121],"a":[38,96],"good":[39],"is":[42,50],"not":[43,107],"yet":[44],"clear.Thus,":[45],"an":[46],"\"iterative":[47],"seeding\"":[48],"framework":[49,59,81],"proposed":[51],"for":[52],"bootstrapping":[53,89],"its":[56],"cost.Our":[58],"iteratively":[60],"selects":[61],"instance":[64,76],"that":[65,103,118,124],"best":[68],"\"goodness":[69],"seed\"":[71],"and":[72],"labels":[73],"set.Our":[80],"deepens":[82],"understanding":[83],"this":[85],"seeding":[86],"process":[87],"by":[90],"deriving":[91],"dual":[93],"problem.We":[94],"propose":[95],"method":[97],"called":[98],"expected":[99],"model":[100],"rotation":[101],"(EMR)":[102],"works":[104],"well":[105],"on":[106,131],"well-separated":[108],"data":[109,133],"which":[110],"frequently":[111],"occur":[112],"as":[113],"realistic":[114,132],"data.Experimental":[115],"results":[116],"show":[117],"EMR":[119],"sets":[123],"provide":[125],"significantly":[126],"higher":[127],"mean":[128],"reciprocal":[129],"rank":[130],"than":[134],"existing":[135],"naive":[136],"selection":[137],"methods":[138],"or":[139],"random":[140],"sets.":[142]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}