{"id":"https://openalex.org/W2758045102","doi":"https://doi.org/10.18653/v1/d17-1251","title":"Never Abandon Minorities: Exhaustive Extraction of Bursty Phrases on Microblogs Using Set Cover Problem","display_name":"Never Abandon Minorities: Exhaustive Extraction of Bursty Phrases on Microblogs Using Set Cover Problem","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2758045102","doi":"https://doi.org/10.18653/v1/d17-1251","mag":"2758045102"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d17-1251","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1251","pdf_url":"https://www.aclweb.org/anthology/D17-1251.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 the 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D17-1251.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010966769","display_name":"Masumi Shirakawa","orcid":null},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masumi Shirakawa","raw_affiliation_strings":["Graduate School of Information Science and Technology, Osaka University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Osaka University, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012025870","display_name":"Takahiro Hara","orcid":"https://orcid.org/0000-0003-4807-3156"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takahiro Hara","raw_affiliation_strings":["hapicom Inc., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"hapicom Inc., Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039456378","display_name":"Takuya Maekawa","orcid":"https://orcid.org/0000-0002-7227-580X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takuya Maekawa","raw_affiliation_strings":["hapicom Inc., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"hapicom Inc., Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2358","last_page":"2367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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":0.9983999729156494,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9979000091552734,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9958999752998352,"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/noun-phrase","display_name":"Noun phrase","score":0.8332693576812744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8042739629745483},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7344914674758911},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.6624295115470886},{"id":"https://openalex.org/keywords/microblogging","display_name":"Microblogging","score":0.6550552845001221},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5999374985694885},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5489287376403809},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5408353209495544},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5012869834899902},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.4533675014972687},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.41030025482177734},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.288656622171402},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11759132146835327}],"concepts":[{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.8332693576812744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8042739629745483},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7344914674758911},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.6624295115470886},{"id":"https://openalex.org/C143275388","wikidata":"https://www.wikidata.org/wiki/Q92438","display_name":"Microblogging","level":3,"score":0.6550552845001221},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5999374985694885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5489287376403809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5408353209495544},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5012869834899902},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.4533675014972687},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.41030025482177734},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.288656622171402},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11759132146835327},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d17-1251","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1251","pdf_url":"https://www.aclweb.org/anthology/D17-1251.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 the 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d17-1251","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1251","pdf_url":"https://www.aclweb.org/anthology/D17-1251.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 the 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4630788492","display_name":null,"funder_award_id":"2620013","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320338124","display_name":"Strategic International Collaborative Research Program","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2758045102.pdf","grobid_xml":"https://content.openalex.org/works/W2758045102.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W11244355","https://openalex.org/W165283731","https://openalex.org/W165525898","https://openalex.org/W188483116","https://openalex.org/W232057064","https://openalex.org/W1514461580","https://openalex.org/W1901600440","https://openalex.org/W1969568357","https://openalex.org/W1982029265","https://openalex.org/W1996531611","https://openalex.org/W1998032016","https://openalex.org/W2011949237","https://openalex.org/W2018165284","https://openalex.org/W2018218137","https://openalex.org/W2077669887","https://openalex.org/W2125099364","https://openalex.org/W2137553870","https://openalex.org/W2150815390","https://openalex.org/W2154756108","https://openalex.org/W2157054705","https://openalex.org/W2168400688","https://openalex.org/W2250899105","https://openalex.org/W2278635123"],"related_works":["https://openalex.org/W2053241453","https://openalex.org/W2017590198","https://openalex.org/W2275433313","https://openalex.org/W2978974359","https://openalex.org/W2153980712","https://openalex.org/W2087532526","https://openalex.org/W2728430307","https://openalex.org/W1805578373","https://openalex.org/W2107786128","https://openalex.org/W2036556872"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,33,77],"language-independent":[3],"datadriven":[4],"method":[5,57,93],"to":[6],"exhaustively":[7],"extract":[8],"bursty":[9,47,52,62,72,81],"phrases":[10,15,63],"of":[11,29,32,38,61,80,104],"arbitrary":[12],"forms":[13],"(e.g.,":[14],"other":[16,45],"than":[17],"simple":[18],"noun":[19,96],"phrases)":[20],"from":[21],"microblogs.":[22],"The":[23],"burst":[24,37],"(i.e.,":[25],"the":[26,30,36,55,59,65,91],"rapid":[27],"increase":[28],"occurrence)":[31],"phrase":[34],"causes":[35],"overlapping":[39],"Ngrams":[40],"including":[41],"incomplete":[42,48],"ones.":[43],"In":[44],"words,":[46],"N-grams":[49,73],"inevitably":[50],"overlap":[51],"phrases.":[53,82],"Thus,":[54],"proposed":[56,92],"performs":[58],"extraction":[60],"as":[64],"set":[66,79],"cover":[67],"problem":[68],"in":[69,102],"which":[70],"all":[71],"are":[74],"covered":[75],"by":[76],"minimum":[78],"Experimental":[83],"results":[84],"using":[85],"Japanese":[86],"Twitter":[87],"data":[88],"showed":[89],"that":[90],"outperformed":[94],"word-based,":[95],"phrase-based,":[97],"and":[98,106],"segmentation-based":[99],"methods":[100],"both":[101],"terms":[103],"accuracy":[105],"coverage.":[107]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}