{"id":"https://openalex.org/W2087787226","doi":"https://doi.org/10.1145/1458082.1458243","title":"Extremely fast text feature extraction for classification and indexing","display_name":"Extremely fast text feature extraction for classification and indexing","publication_year":2008,"publication_date":"2008-10-26","ids":{"openalex":"https://openalex.org/W2087787226","doi":"https://doi.org/10.1145/1458082.1458243","mag":"2087787226"},"language":"en","primary_location":{"id":"doi:10.1145/1458082.1458243","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM 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/A5077348567","display_name":"George Forman","orcid":"https://orcid.org/0000-0003-2179-4930"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"George Forman","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022565584","display_name":"Evan Kirshenbaum","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evan Kirshenbaum","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077348567"],"corresponding_institution_ids":["https://openalex.org/I1324840837"],"apc_list":null,"apc_paid":null,"fwci":6.2925,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.96136635,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1221","last_page":"1230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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":0.996999979019165,"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":0.9952999949455261,"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":0.8468829393386841},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7742229700088501},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6881688833236694},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6283034086227417},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6105908751487732},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6067025661468506},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5927752256393433},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.546364963054657},{"id":"https://openalex.org/keywords/unicode","display_name":"Unicode","score":0.4927976429462433},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4864206314086914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4508698284626007},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39726823568344116},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3783644437789917},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3584519624710083},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21315783262252808},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09562581777572632}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8468829393386841},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7742229700088501},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6881688833236694},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6283034086227417},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6105908751487732},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6067025661468506},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5927752256393433},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.546364963054657},{"id":"https://openalex.org/C500551929","wikidata":"https://www.wikidata.org/wiki/Q8819","display_name":"Unicode","level":2,"score":0.4927976429462433},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4864206314086914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4508698284626007},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39726823568344116},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3783644437789917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3584519624710083},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21315783262252808},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09562581777572632},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1458082.1458243","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM 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":0.5400000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W100509257","https://openalex.org/W199391036","https://openalex.org/W1570448133","https://openalex.org/W1577337656","https://openalex.org/W1604321289","https://openalex.org/W1605569224","https://openalex.org/W1970659131","https://openalex.org/W1972418517","https://openalex.org/W2035720976","https://openalex.org/W2099964107","https://openalex.org/W2103333826","https://openalex.org/W2126795708","https://openalex.org/W2150166339","https://openalex.org/W2326587081","https://openalex.org/W2752853835","https://openalex.org/W2966207845","https://openalex.org/W3198160809"],"related_works":["https://openalex.org/W1953677193","https://openalex.org/W3113362864","https://openalex.org/W2041478992","https://openalex.org/W4232755842","https://openalex.org/W2144265691","https://openalex.org/W1567515080","https://openalex.org/W1605991620","https://openalex.org/W113683524","https://openalex.org/W4387251676","https://openalex.org/W4385261619"],"abstract_inverted_index":{"Most":[0],"research":[1],"in":[2,77],"speeding":[3],"up":[4],"text":[5,51],"mining":[6],"involves":[7],"algorithmic":[8],"improvements":[9],"to":[10,83],"induction":[11],"algorithms,":[12],"and":[13,64,95],"yet":[14],"for":[15,50],"many":[16],"large":[17,25],"scale":[18],"applications,":[19],"such":[20],"as":[21],"classifying":[22],"or":[23],"indexing":[24],"document":[26],"repositories,":[27],"the":[28,40],"time":[29],"spent":[30],"extracting":[31],"word":[32,61,88],"features":[33,75],"from":[34],"texts":[35],"can":[36],"itself":[37],"greatly":[38],"exceed":[39],"initial":[41],"training":[42],"time.":[43],"This":[44],"paper":[45],"describes":[46],"a":[47],"fast":[48],"method":[49],"feature":[52],"extraction":[53],"that":[54,71],"folds":[55],"together":[56],"Unicode":[57],"conversion,":[58],"forced":[59],"lowercasing,":[60],"boundary":[62],"detection,":[63],"string":[65,87],"hash":[66,74],"computation.":[67],"We":[68],"show":[69],"empirically":[70],"our":[72],"integer":[73],"result":[76],"classifiers":[78],"with":[79],"equivalent":[80],"statistical":[81],"performance":[82],"those":[84],"built":[85],"using":[86],"features,":[89],"but":[90],"require":[91],"far":[92],"less":[93,96],"computation":[94],"memory.":[97]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}