{"id":"https://openalex.org/W1514969207","doi":null,"title":"Not All Seeds Are Equal: Measuring the Quality of Text Mining Seeds","display_name":"Not All Seeds Are Equal: Measuring the Quality of Text Mining Seeds","publication_year":2010,"publication_date":"2010-06-02","ids":{"openalex":"https://openalex.org/W1514969207","mag":"1514969207"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.183.2933","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.183.2933","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isi.edu/%7Ekozareva/papers/kozareva_goodness_seeds_naacl10.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5007532004","display_name":"Zornitsa Kozareva","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zornitsa Kozareva","raw_affiliation_strings":["USC Information Sciences Institute, Marina del rey, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute, Marina del rey, CA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060225743","display_name":"Eduard H. Hovy","orcid":"https://orcid.org/0000-0002-3270-7903","observed_orcids":["https://orcid.org/0000-0002-3270-7903"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eduard Hovy","raw_affiliation_strings":["USC Information Sciences Institute, Marina del rey, CA"],"raw_orcid":"https://orcid.org/0000-0002-3270-7903","affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute, Marina del rey, CA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7384,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.95859041,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"618","last_page":"626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.739300012588501,"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":0.739300012588501,"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":0.10109999775886536,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.0551999993622303,"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/bootstrap-method","display_name":"bootstrapping","score":0.9319999814033508},{"id":"https://openalex.org/keywords/regression-models","display_name":"regression models","score":0.5070000290870667},{"id":"https://openalex.org/keywords/knowledge-harvesting","display_name":"knowledge harvesting","score":0.7279999852180481},{"id":"https://openalex.org/keywords/relation-types","display_name":"relation types","score":0.42100000381469727}],"concepts":[{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.8682023286819458},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7121139168739319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.597463846206665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5700240135192871},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5694772005081177},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5259761214256287},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4784848093986511},{"id":"https://openalex.org/C132480984","wikidata":"https://www.wikidata.org/wiki/Q2034239","display_name":"Goodness of fit","level":2,"score":0.4778042435646057},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.44299203157424927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4248954653739929},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38655561208724976},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3459841310977936},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3247002959251404},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.31675469875335693},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.1351553499698639},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.183.2933","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.183.2933","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isi.edu/%7Ekozareva/papers/kozareva_goodness_seeds_naacl10.pdf","raw_type":"text"},{"id":"mag:1514969207","doi":null,"is_oa":false,"landing_page_url":"https://people.cs.pitt.edu/~litman/courses/cs2710/papers/kozareva_goodness_seeds_naacl10.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W197270748","https://openalex.org/W1560724230","https://openalex.org/W1570448133","https://openalex.org/W1588490261","https://openalex.org/W1964357740","https://openalex.org/W2013109830","https://openalex.org/W2019496358","https://openalex.org/W2022166150","https://openalex.org/W2057052429","https://openalex.org/W2068737686","https://openalex.org/W2068882115","https://openalex.org/W2080856991","https://openalex.org/W2098688754","https://openalex.org/W2100869678","https://openalex.org/W2103296194","https://openalex.org/W2127978399","https://openalex.org/W2137226992","https://openalex.org/W2142305207","https://openalex.org/W2145328028","https://openalex.org/W2148540243","https://openalex.org/W2277582207","https://openalex.org/W2337482790","https://openalex.org/W2600716915","https://openalex.org/W2882319491","https://openalex.org/W2966207845"],"related_works":["https://openalex.org/W7098644762","https://openalex.org/W7098773380","https://openalex.org/W2107322005","https://openalex.org/W7099553681","https://openalex.org/W7097317845","https://openalex.org/W2251917898","https://openalex.org/W2104108827","https://openalex.org/W2170670430","https://openalex.org/W2550527484","https://openalex.org/W2132928286"],"abstract_inverted_index":{"Open-class":[0],"semantic":[1,27],"lexicon":[2],"induction":[3],"is":[4,67],"of":[5,32,45,58,73],"great":[6],"interest":[7],"for":[8,29,80],"current":[9],"knowledge":[10],"harvesting":[11],"algorithms.":[12],"We":[13],"propose":[14],"a":[15,50],"general":[16],"framework":[17],"that":[18,53],"uses":[19],"patterns":[20,35],"in":[21],"bootstrapping":[22],"fashion":[23],"to":[24],"learn":[25],"open-class":[26],"lexicons":[28],"different":[30,71,78],"kinds":[31,72],"relations.":[33],"These":[34],"require":[36],"seeds.":[37],"To":[38],"estimate":[39],"the":[40,55,59],"goodness":[41],"(the":[42],"potential":[43],"yield)":[44],"new":[46],"seeds,":[47],"we":[48],"introduce":[49],"regression":[51,65],"model":[52,66],"considers":[54],"connectivity":[56],"behavior":[57],"seed":[60],"during":[61],"bootstrapping.":[62],"The":[63],"generalized":[64],"evaluated":[68],"on":[69],"six":[70],"relations":[74],"with":[75],"over":[76],"10000":[77],"seeds":[79],"English":[81],"and":[82],"Spanish":[83],"patterns.":[84],"Our":[85],"approach":[86],"reaches":[87],"robust":[88],"performance":[89]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":4}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}