{"id":"https://openalex.org/W2547601809","doi":"https://doi.org/10.1109/iscslp.2016.7918480","title":"Exploiting noisy web data by OOV ranking for low-resource keyword search","display_name":"Exploiting noisy web data by OOV ranking for low-resource keyword search","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2547601809","doi":"https://doi.org/10.1109/iscslp.2016.7918480","mag":"2547601809"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100325075","display_name":"Zhipeng Chen","orcid":"https://orcid.org/0000-0001-6444-192X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Chen","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014958566","display_name":"Ji Wu","orcid":"https://orcid.org/0000-0001-6170-726X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Wu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9984999895095825,"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":0.9980999827384949,"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":0.8304882049560547},{"id":"https://openalex.org/keywords/keyword-density","display_name":"Keyword density","score":0.5840867757797241},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5754027962684631},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5701878070831299},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5655558109283447},{"id":"https://openalex.org/keywords/zipfs-law","display_name":"Zipf's law","score":0.5556702017784119},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5217969417572021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5164504051208496},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5065375566482544},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4917438328266144},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43517494201660156},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.432695597410202},{"id":"https://openalex.org/keywords/keyword-search","display_name":"Keyword search","score":0.34952473640441895},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09534263610839844},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07573196291923523},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07271173596382141}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8304882049560547},{"id":"https://openalex.org/C57560718","wikidata":"https://www.wikidata.org/wiki/Q125627","display_name":"Keyword density","level":3,"score":0.5840867757797241},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5754027962684631},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5701878070831299},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5655558109283447},{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.5556702017784119},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5217969417572021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5164504051208496},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5065375566482544},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4917438328266144},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43517494201660156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.432695597410202},{"id":"https://openalex.org/C2988412617","wikidata":"https://www.wikidata.org/wiki/Q7441656","display_name":"Keyword search","level":2,"score":0.34952473640441895},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09534263610839844},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07573196291923523},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07271173596382141},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iscslp.2016.7918480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},{"id":"mag:3161168029","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=201702253221284102","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W51407305","https://openalex.org/W265531733","https://openalex.org/W1506752962","https://openalex.org/W1524333225","https://openalex.org/W1596222676","https://openalex.org/W1631260214","https://openalex.org/W2005232502","https://openalex.org/W2025198378","https://openalex.org/W2026369565","https://openalex.org/W2028148926","https://openalex.org/W2030119804","https://openalex.org/W2094971681","https://openalex.org/W2105830342","https://openalex.org/W2110817634","https://openalex.org/W2117278770","https://openalex.org/W2131342762","https://openalex.org/W2150857077","https://openalex.org/W2156431836","https://openalex.org/W2165921245","https://openalex.org/W2167338739","https://openalex.org/W2407420912","https://openalex.org/W6602125538","https://openalex.org/W6609831787","https://openalex.org/W6631362777","https://openalex.org/W6636811518","https://openalex.org/W6675840953","https://openalex.org/W6677328538","https://openalex.org/W6683369307","https://openalex.org/W6684509081","https://openalex.org/W6713813099"],"related_works":["https://openalex.org/W2197440050","https://openalex.org/W2614415116","https://openalex.org/W2265184183","https://openalex.org/W2466354565","https://openalex.org/W1993927003","https://openalex.org/W2011694694","https://openalex.org/W1496822620","https://openalex.org/W1964343189","https://openalex.org/W2396810046","https://openalex.org/W2737182486"],"abstract_inverted_index":{"Spoken":[0],"keyword":[1,90,104,122],"search":[2],"in":[3],"low-resource":[4],"condition":[5],"suffers":[6],"from":[7,51,74],"out-of-vocabulary":[8],"(OOV)":[9],"problem":[10],"and":[11,28,39,79,128,139],"insufficient":[12],"text":[13,21,38,126],"data":[14,22,43,53,76,145],"for":[15,84,110,144],"language":[16,31],"model":[17],"(LM)":[18],"training.":[19],"Web-crawled":[20],"is":[23,133],"used":[24,81,109,141],"to":[25,29,46,57,70,97,135],"expand":[26,98],"vocabulary":[27],"augment":[30],"model.":[32],"However,":[33],"the":[34,40,88,99,102],"mismatching":[35],"between":[36],"web":[37,52,75],"target":[41],"speech":[42],"brings":[44],"difficulties":[45],"effective":[47],"utilization.":[48],"New":[49],"words":[50,60,73,94,107],"need":[54],"an":[55],"evaluation":[56],"exclude":[58],"noisy":[59],"or":[61],"introduce":[62],"proper":[63],"probabilities.":[64],"In":[65,87,101],"this":[66,131],"paper,":[67],"several":[68],"criteria":[69],"rank":[71],"new":[72],"are":[77,80,95,108,115],"investigated":[78],"as":[82],"features":[83],"logistic":[85],"regression.":[86],"IV":[89],"case,":[91,105],"top":[92],"N":[93],"selected":[96],"vocabulary.":[100],"OOV":[103],"all":[106],"expansion":[111],"but":[112],"unigram":[113],"probabilities":[114],"re-assigned":[116],"by":[117],"Zipf's":[118],"law.":[119],"On":[120],"Swahili":[121],"search,":[123],"after":[124],"further":[125],"filtering":[127],"LM":[129],"interpolation,":[130],"strategy":[132],"observed":[134],"outperform":[136],"a":[137],"strong":[138],"commonly":[140],"baseline":[142],"method":[143],"selection.":[146]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}