{"id":"https://openalex.org/W2260244612","doi":"https://doi.org/10.1145/2835776.2835778","title":"Long-tail Vocabulary Dictionary Extraction from the Web","display_name":"Long-tail Vocabulary Dictionary Extraction from the Web","publication_year":2016,"publication_date":"2016-02-04","ids":{"openalex":"https://openalex.org/W2260244612","doi":"https://doi.org/10.1145/2835776.2835778","mag":"2260244612"},"language":"en","primary_location":{"id":"doi:10.1145/2835776.2835778","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2835776.2835778","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2835776.2835778","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2835776.2835778","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100457678","display_name":"Zhe Chen","orcid":"https://orcid.org/0000-0002-2919-4481"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhe Chen","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039133265","display_name":"Michael Cafarella","orcid":"https://orcid.org/0000-0001-6122-0590"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Cafarella","raw_affiliation_strings":["University of Michigan, Ann arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087012731","display_name":"H. V. Jagadish","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. V. Jagadish","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100457678"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":19.3925,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.99164081,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"625","last_page":"634"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9965000152587891,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9933000206947327,"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":0.8245357275009155},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6883389353752136},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6809540390968323},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6185689568519592},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6029199361801147},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5607873201370239},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5493147969245911},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5107934474945068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48168548941612244},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.43996235728263855},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4388887584209442},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4278002977371216},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09082087874412537},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06103760004043579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8245357275009155},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6883389353752136},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6809540390968323},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6185689568519592},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6029199361801147},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5607873201370239},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5493147969245911},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5107934474945068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48168548941612244},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.43996235728263855},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4388887584209442},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4278002977371216},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09082087874412537},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06103760004043579},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2835776.2835778","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2835776.2835778","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2835776.2835778","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2835776.2835778","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2835776.2835778","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2835776.2835778","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1382434068","display_name":"CAREER: Building and Searching a Structured Web Database","funder_award_id":"1054913","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G788312519","display_name":null,"funder_award_id":"IIS-1054913","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2260244612.pdf","grobid_xml":"https://content.openalex.org/works/W2260244612.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1489949474","https://openalex.org/W1493490255","https://openalex.org/W1553019137","https://openalex.org/W1670132599","https://openalex.org/W1870305865","https://openalex.org/W1982242209","https://openalex.org/W2016753842","https://openalex.org/W2027081355","https://openalex.org/W2048679005","https://openalex.org/W2080132606","https://openalex.org/W2103296194","https://openalex.org/W2103333826","https://openalex.org/W2103931177","https://openalex.org/W2104086170","https://openalex.org/W2104987630","https://openalex.org/W2107598941","https://openalex.org/W2110367654","https://openalex.org/W2114998795","https://openalex.org/W2117510361","https://openalex.org/W2122052811","https://openalex.org/W2125972432","https://openalex.org/W2146304342","https://openalex.org/W2147880316","https://openalex.org/W2148540243","https://openalex.org/W2169753664","https://openalex.org/W2250265269","https://openalex.org/W2251623545","https://openalex.org/W2295058825","https://openalex.org/W2785349534","https://openalex.org/W2999159947","https://openalex.org/W3098372638","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2035261173","https://openalex.org/W2138922887","https://openalex.org/W2125109223","https://openalex.org/W2383063829","https://openalex.org/W2358294942","https://openalex.org/W2082678934"],"abstract_inverted_index":{"A":[0],"dictionary":[1],"---":[2,13],"a":[3,21,43],"set":[4],"of":[5],"instances":[6],"belonging":[7],"to":[8,16,49],"the":[9],"same":[10],"conceptual":[11],"class":[12],"is":[14,20],"central":[15],"information":[17],"extraction":[18],"and":[19,31,59],"useful":[22],"primitive":[23],"for":[24],"many":[25],"applications,":[26],"including":[27],"query":[28],"log":[29],"analysis":[30],"document":[32],"categorization.":[33],"Considerable":[34],"work":[35],"has":[36],"focused":[37],"on":[38],"generating":[39],"accurate":[40],"dictionaries":[41],"given":[42],"few":[44],"example":[45],"seeds,":[46],"but":[47],"methods":[48],"date":[50],"cannot":[51],"obtain":[52],"long-tail":[53],"(rare)":[54],"items":[55],"with":[56],"high":[57],"accuracy":[58],"recall.":[60]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":4}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}