{"id":"https://openalex.org/W2127241642","doi":"https://doi.org/10.1145/2484028.2484142","title":"The bag-of-repeats representation of documents","display_name":"The bag-of-repeats representation of documents","publication_year":2013,"publication_date":"2013-07-28","ids":{"openalex":"https://openalex.org/W2127241642","doi":"https://doi.org/10.1145/2484028.2484142","mag":"2127241642"},"language":"en","primary_location":{"id":"doi:10.1145/2484028.2484142","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484028.2484142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval","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/A5074485795","display_name":"Matthias Gall\u00e9","orcid":"https://orcid.org/0000-0001-5677-5911"},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Matthias Gall\u00e9","raw_affiliation_strings":["Xerox Research Centre Europe, Meylan, France","Xerox Research Centre Europe, Meylan, France#TAB#"],"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan, France","institution_ids":["https://openalex.org/I33976269"]},{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan, France#TAB#","institution_ids":["https://openalex.org/I33976269"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5074485795"],"corresponding_institution_ids":["https://openalex.org/I33976269"],"apc_list":null,"apc_paid":null,"fwci":1.9237,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88710944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1053","last_page":"1056"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing 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/T10181","display_name":"Natural Language Processing 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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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/representation","display_name":"Representation (politics)","score":0.7504065036773682},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6647930145263672},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.6646959185600281},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6613126993179321},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6581461429595947},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6230718493461609},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.5741024017333984},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5619281530380249},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.529508113861084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5027682781219482},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4938219487667084},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.459343284368515},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.42322662472724915},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2723618149757385},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.12325996160507202},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.10796195268630981},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09093785285949707},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.07244616746902466}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7504065036773682},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6647930145263672},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.6646959185600281},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6613126993179321},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6581461429595947},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6230718493461609},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.5741024017333984},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5619281530380249},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.529508113861084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5027682781219482},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4938219487667084},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.459343284368515},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.42322662472724915},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2723618149757385},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.12325996160507202},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.10796195268630981},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09093785285949707},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.07244616746902466},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2484028.2484142","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484028.2484142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W68251067","https://openalex.org/W102175118","https://openalex.org/W611246771","https://openalex.org/W1480643256","https://openalex.org/W1504417041","https://openalex.org/W1546910080","https://openalex.org/W1550172732","https://openalex.org/W1575949727","https://openalex.org/W1596093948","https://openalex.org/W1909028788","https://openalex.org/W1970825859","https://openalex.org/W1971140524","https://openalex.org/W1990061958","https://openalex.org/W2018647136","https://openalex.org/W2020842694","https://openalex.org/W2024657257","https://openalex.org/W2059504991","https://openalex.org/W2069263150","https://openalex.org/W2097394335","https://openalex.org/W2104210067","https://openalex.org/W2134941170","https://openalex.org/W2143296986","https://openalex.org/W2169606435","https://openalex.org/W2174706414","https://openalex.org/W2179142997","https://openalex.org/W2213947579","https://openalex.org/W2246025837","https://openalex.org/W4213138647","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4236073812","https://openalex.org/W2053389710","https://openalex.org/W3048777016","https://openalex.org/W4237719335","https://openalex.org/W1547487846","https://openalex.org/W2528236455","https://openalex.org/W3135525638","https://openalex.org/W3126099397","https://openalex.org/W3001910530","https://openalex.org/W1518351784"],"abstract_inverted_index":{"n-gram":[0],"representations":[1],"of":[2,16,27,37],"documents":[3],"may":[4],"improve":[5],"over":[6],"a":[7,25],"simple":[8],"bag-of-word":[9],"representation":[10],"by":[11],"relaxing":[12],"the":[13,35,38],"independence":[14],"assumption":[15],"word":[17],"and":[18,33],"introducing":[19],"context.":[20],"However,":[21],"this":[22],"comes":[23],"at":[24],"cost":[26],"adding":[28],"features":[29],"which":[30],"are":[31],"non-descriptive,":[32],"increasing":[34],"dimension":[36],"vector":[39],"space":[40],"model":[41],"exponentially.":[42]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}