{"id":"https://openalex.org/W1971323086","doi":"https://doi.org/10.1145/1871437.1871520","title":"Language pyramid and multi-scale text analysis","display_name":"Language pyramid and multi-scale text analysis","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W1971323086","doi":"https://doi.org/10.1145/1871437.1871520","mag":"1971323086"},"language":"en","primary_location":{"id":"doi:10.1145/1871437.1871520","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and 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/A5108432183","display_name":"Shuang-Hong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shuang-Hong Yang","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Georgia Institute of Technology Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046703129","display_name":"Hongyuan Zha","orcid":"https://orcid.org/0000-0001-7493-0911"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongyuan Zha","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Georgia Institute of Technology Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5108432183"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.8042,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.86463384,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"639","last_page":"648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9993000030517578,"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":0.9991999864578247,"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":0.808232843875885},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6704599857330322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6331984996795654},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5145260691642761},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.503452718257904},{"id":"https://openalex.org/keywords/explicit-semantic-analysis","display_name":"Explicit semantic analysis","score":0.47627609968185425},{"id":"https://openalex.org/keywords/noisy-text-analytics","display_name":"Noisy text analytics","score":0.474041223526001},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.46486955881118774},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4405047595500946},{"id":"https://openalex.org/keywords/text-graph","display_name":"Text graph","score":0.2440771460533142},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.15416327118873596},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.1122359037399292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.808232843875885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6704599857330322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6331984996795654},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5145260691642761},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.503452718257904},{"id":"https://openalex.org/C173862523","wikidata":"https://www.wikidata.org/wiki/Q5421270","display_name":"Explicit semantic analysis","level":5,"score":0.47627609968185425},{"id":"https://openalex.org/C151375590","wikidata":"https://www.wikidata.org/wiki/Q17147076","display_name":"Noisy text analytics","level":4,"score":0.474041223526001},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.46486955881118774},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4405047595500946},{"id":"https://openalex.org/C66945725","wikidata":"https://www.wikidata.org/wiki/Q18388823","display_name":"Text graph","level":3,"score":0.2440771460533142},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.15416327118873596},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.1122359037399292},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.0},{"id":"https://openalex.org/C6881194","wikidata":"https://www.wikidata.org/wiki/Q7449091","display_name":"Semantic technology","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1871437.1871520","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1480643256","https://openalex.org/W1491101954","https://openalex.org/W1574901103","https://openalex.org/W1583700199","https://openalex.org/W1972594981","https://openalex.org/W1973234918","https://openalex.org/W2025356973","https://openalex.org/W2031823405","https://openalex.org/W2070740689","https://openalex.org/W2071664212","https://openalex.org/W2084809122","https://openalex.org/W2086004682","https://openalex.org/W2093390569","https://openalex.org/W2095368471","https://openalex.org/W2097308346","https://openalex.org/W2103504761","https://openalex.org/W2112874453","https://openalex.org/W2113765418","https://openalex.org/W2114811871","https://openalex.org/W2115346359","https://openalex.org/W2117612778","https://openalex.org/W2120084270","https://openalex.org/W2127836646","https://openalex.org/W2130747910","https://openalex.org/W2143539328","https://openalex.org/W2143693569","https://openalex.org/W2145295623","https://openalex.org/W2148540243","https://openalex.org/W2150102617","https://openalex.org/W2151103935","https://openalex.org/W2159518412","https://openalex.org/W2163382007","https://openalex.org/W2170741935","https://openalex.org/W2293656538","https://openalex.org/W2423725643","https://openalex.org/W2435251607","https://openalex.org/W2596701210","https://openalex.org/W2963165956","https://openalex.org/W3086441338","https://openalex.org/W4206765718","https://openalex.org/W4285719527","https://openalex.org/W4300073824"],"related_works":["https://openalex.org/W1978572805","https://openalex.org/W2383807498","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W1972594981","https://openalex.org/W2136542423","https://openalex.org/W2045966063","https://openalex.org/W2134461492","https://openalex.org/W3129054449"],"abstract_inverted_index":{"The":[0,99],"classical":[1],"Bag-of-Word":[2],"(BOW)":[3],"model":[4],"represents":[5],"a":[6,9,38,41,51,70,73,85,90,109],"document":[7,39,71,128],"as":[8,40],"histogram":[10],"of":[11,69,75,87,111],"word":[12],"occurrence,":[13],"losing":[14],"the":[15,31,45,120,179],"spatial":[16,67],"information":[17],"that":[18,77],"is":[19],"invaluable":[20],"for":[21,57,95,127,135,144,167],"many":[22],"text":[23,59,106,125,138,157],"analysis":[24,107],"tasks.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29,115],"present":[30],"Language":[32],"Pyramid":[33],"(LaP)":[34],"model,":[35],"which":[36,114],"casts":[37],"probabilistic":[42],"distribution":[43],"over":[44,174],"joint":[46],"semantic-spatial":[47],"space":[48],"and":[49,66,82,130,159,166],"motivates":[50],"multi-scale":[52,92,124,132],"2D":[53],"local":[54],"smoothing":[55],"framework":[56],"nonparametric":[58],"coding.":[60],"LaP":[61,100,146,169],"efficiently":[62],"encodes":[63],"both":[64,80],"semantic":[65],"contents":[68],"into":[72],"pyramid":[74],"matrices":[76],"are":[78],"smoothed":[79],"semantically":[81],"spatially":[83],"at":[84],"sequence":[86],"resolutions,":[88],"providing":[89],"convenient":[91],"imagic":[93],"view":[94],"natural":[96],"language":[97,133,176],"understanding.":[98],"representation":[101],"can":[102],"be":[103],"used":[104],"in":[105,108,119],"variety":[110],"ways,":[112],"among":[113],"investigate":[116],"two":[117],"instantiations":[118],"current":[121],"paper:":[122],"(1)":[123],"kernels":[126],"categorization,":[129],"(2)":[131],"models":[134,177],"ad":[136],"hoc":[137],"retrieval.":[139],"Experimental":[140],"results":[141],"illustrate":[142],"that:":[143],"classification,":[145],"outperforms":[147],"BOW":[148],"by":[149],"(up":[150],"to)":[151],"4%":[152],"on":[153,161,178],"moderate-length":[154],"texts":[155,163],"(RCV1":[156],"benchmark)":[158],"15%":[160],"short":[162],"(Yahoo!":[164],"queries);":[165],"retrieval,":[168],"gains":[170],"12%":[171],"MAP":[172],"improvement":[173],"uni-gram":[175],"OHSUMED":[180],"data":[181],"set.":[182]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}