{"id":"https://openalex.org/W3094588044","doi":"https://doi.org/10.1145/3340531.3412029","title":"Mining Infrequent High-Quality Phrases from Domain-Specific Corpora","display_name":"Mining Infrequent High-Quality Phrases from Domain-Specific Corpora","publication_year":2020,"publication_date":"2020-10-19","ids":{"openalex":"https://openalex.org/W3094588044","doi":"https://doi.org/10.1145/3340531.3412029","mag":"3094588044"},"language":"en","primary_location":{"id":"doi:10.1145/3340531.3412029","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"article","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/A5116736541","display_name":"Li Wang","orcid":"https://orcid.org/0000-0003-4415-045X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li Wang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339289","display_name":"Wei Zhu","orcid":"https://orcid.org/0000-0002-6389-6866"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Zhu","raw_affiliation_strings":["Pingan Health Technology, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Pingan Health Technology, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103193321","display_name":"Sihang Jiang","orcid":"https://orcid.org/0000-0002-0736-6457"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sihang Jiang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394022","display_name":"Sheng Zhang","orcid":"https://orcid.org/0000-0002-6581-6399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng Zhang","raw_affiliation_strings":["Pingan Health Technology, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Pingan Health Technology, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101554486","display_name":"Keqiang Wang","orcid":"https://orcid.org/0000-0002-5322-365X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keqiang Wang","raw_affiliation_strings":["Pingan Health Technology, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Pingan Health Technology, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112115522","display_name":"Yuan Ni","orcid":"https://orcid.org/0000-0002-9672-3531"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Ni","raw_affiliation_strings":["Pingan Health Technology, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Pingan Health Technology, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023775139","display_name":"Guotong Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guotong Xie","raw_affiliation_strings":["Pingan Health Technology, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Pingan Health Technology, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090455375","display_name":"Yanghua Xiao","orcid":"https://orcid.org/0000-0001-8403-9591"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanghua Xiao","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5116736541"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.193,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.83838346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1535","last_page":"1544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis 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/T13083","display_name":"Advanced Text Analysis 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":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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":0.8567135334014893},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.714687168598175},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6581023335456848},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.6362773776054382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6110220551490784},{"id":"https://openalex.org/keywords/noun-phrase","display_name":"Noun phrase","score":0.5948650240898132},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.510525107383728},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48332974314689636},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47553539276123047},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4324984848499298},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4261699914932251},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3339468240737915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8567135334014893},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.714687168598175},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6581023335456848},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.6362773776054382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6110220551490784},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.5948650240898132},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.510525107383728},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48332974314689636},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47553539276123047},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4324984848499298},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4261699914932251},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3339468240737915},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3340531.3412029","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1525595230","https://openalex.org/W1531333757","https://openalex.org/W1541542953","https://openalex.org/W1603598191","https://openalex.org/W1988059434","https://openalex.org/W2049107599","https://openalex.org/W2056132907","https://openalex.org/W2060772621","https://openalex.org/W2064675550","https://openalex.org/W2066066594","https://openalex.org/W2089818016","https://openalex.org/W2099856937","https://openalex.org/W2101926813","https://openalex.org/W2126940099","https://openalex.org/W2147880316","https://openalex.org/W2150815390","https://openalex.org/W2153579005","https://openalex.org/W2154292298","https://openalex.org/W2160517426","https://openalex.org/W2168289837","https://openalex.org/W2223881431","https://openalex.org/W2294957770","https://openalex.org/W2407111606","https://openalex.org/W2539469848","https://openalex.org/W2593560537","https://openalex.org/W2605024074","https://openalex.org/W2612481500","https://openalex.org/W2796254167","https://openalex.org/W2891383691","https://openalex.org/W2906809452","https://openalex.org/W2949995692","https://openalex.org/W2950635152","https://openalex.org/W2963265326","https://openalex.org/W2963345057","https://openalex.org/W2964121744","https://openalex.org/W2966488597"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Phrase":[0],"mining":[1,30],"is":[2,73],"a":[3,81,89,94],"fundamental":[4],"task":[5],"for":[6],"text":[7],"analysis":[8],"and":[9,21,108,116,138],"has":[10],"various":[11],"downstream":[12],"applications":[13],"such":[14],"as":[15],"named":[16],"entity":[17],"recognition,":[18],"topic":[19],"modeling,":[20],"relation":[22],"extraction.":[23],"In":[24,70,84],"this":[25,85],"paper,":[26,86],"we":[27,87,103],"focus":[28],"on":[29,58],"high-quality":[31,47,82],"phrases":[32,48,63],"from":[33],"domain-specific":[34],"corpora":[35,123],"with":[36],"special":[37],"consideration":[38],"of":[39,80],"infrequent":[40,46,100],"ones.":[41],"Previous":[42],"methods":[43,56,134],"might":[44],"miss":[45],"in":[49,77],"the":[50,67,78],"candidate":[51],"selection":[52],"stage.":[53],"And":[54,102],"these":[55],"rely":[57],"explicit":[59],"features":[60,107],"to":[61,98,113],"mine":[62],"while":[64],"rarely":[65,74],"considering":[66],"implicit":[68,105],"features.":[69],"addition,":[71],"completeness":[72],"explicitly":[75],"considered":[76],"evaluation":[79],"phrase.":[83],"propose":[88],"novel":[90],"approach":[91],"that":[92,125],"exploits":[93],"sequence":[95],"labeling":[96],"model":[97],"capture":[99],"phrases.":[101],"employ":[104],"semantic":[106],"contextual":[109],"POS":[110],"tag":[111],"statistics":[112],"measure":[114],"meaningfulness":[115],"completeness,":[117],"respectively.":[118],"Experiments":[119],"over":[120,131],"four":[121],"real-world":[122],"demonstrate":[124],"our":[126],"method":[127],"achieves":[128],"significant":[129],"improvements":[130],"previous":[132],"state-of-the-art":[133],"across":[135],"different":[136],"domains":[137],"languages.":[139]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}