{"id":"https://openalex.org/W2020920215","doi":"https://doi.org/10.1145/2499178.2499180","title":"Textual Similarity with a Bag-of-Embedded-Words Model","display_name":"Textual Similarity with a Bag-of-Embedded-Words Model","publication_year":2013,"publication_date":"2013-09-29","ids":{"openalex":"https://openalex.org/W2020920215","doi":"https://doi.org/10.1145/2499178.2499180","mag":"2020920215"},"language":"en","primary_location":{"id":"doi:10.1145/2499178.2499180","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2499178.2499180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on the Theory of 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/A5031052064","display_name":"St\u00e9phane Clinchant","orcid":"https://orcid.org/0000-0003-2367-8837"},"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":"St\u00e9phane Clinchant","raw_affiliation_strings":["Xerox Research Centre Europe","Xerox Research Centre Europe#TAB#"],"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe","institution_ids":["https://openalex.org/I33976269"]},{"raw_affiliation_string":"Xerox Research Centre Europe#TAB#","institution_ids":["https://openalex.org/I33976269"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059987704","display_name":"Florent Perronnin","orcid":null},"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":false,"raw_author_name":"Florent Perronnin","raw_affiliation_strings":["Xerox Research Centre Europe","Xerox Research Centre Europe#TAB#"],"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe","institution_ids":["https://openalex.org/I33976269"]},{"raw_affiliation_string":"Xerox Research Centre Europe#TAB#","institution_ids":["https://openalex.org/I33976269"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031052064"],"corresponding_institution_ids":["https://openalex.org/I33976269"],"apc_list":null,"apc_paid":null,"fwci":3.3664,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9247789,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","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/T11309","display_name":"Music and Audio Processing","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/word","display_name":"Word (group theory)","score":0.7894415855407715},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.746334433555603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7113944888114929},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6856592893600464},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.635952889919281},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5807874798774719},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5700756311416626},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5251079201698303},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5145799517631531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5115671753883362},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.47415608167648315},{"id":"https://openalex.org/keywords/euclidean-space","display_name":"Euclidean space","score":0.4662116467952728},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.45249199867248535},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.41346651315689087},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2379089593887329},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.12505993247032166},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07720103859901428}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7894415855407715},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.746334433555603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113944888114929},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6856592893600464},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.635952889919281},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5807874798774719},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5700756311416626},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5251079201698303},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5145799517631531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5115671753883362},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.47415608167648315},{"id":"https://openalex.org/C186450821","wikidata":"https://www.wikidata.org/wiki/Q17295","display_name":"Euclidean space","level":2,"score":0.4662116467952728},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.45249199867248535},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.41346651315689087},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2379089593887329},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.12505993247032166},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07720103859901428},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2499178.2499180","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2499178.2499180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on the Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338370","display_name":"FP7 Information and Communication Technologies","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1606858007","https://openalex.org/W1625255723","https://openalex.org/W1880262756","https://openalex.org/W1902027874","https://openalex.org/W1974490937","https://openalex.org/W2071027807","https://openalex.org/W2105157020","https://openalex.org/W2107743791","https://openalex.org/W2112971401","https://openalex.org/W2113459411","https://openalex.org/W2117130368","https://openalex.org/W2137245235","https://openalex.org/W2147238549","https://openalex.org/W2161578080","https://openalex.org/W2165279024","https://openalex.org/W2166473218","https://openalex.org/W2296073425","https://openalex.org/W4233135949"],"related_works":["https://openalex.org/W2186284405","https://openalex.org/W2062849642","https://openalex.org/W2372154248","https://openalex.org/W1984733048","https://openalex.org/W2951029798","https://openalex.org/W2151108588","https://openalex.org/W2349125667","https://openalex.org/W2522836003","https://openalex.org/W776182271","https://openalex.org/W2125001968"],"abstract_inverted_index":{"While":[0],"words":[1],"in":[2,14,61,66,71,82],"documents":[3],"are":[4,88],"generally":[5],"treated":[6],"as":[7,38],"discrete":[8],"entities,":[9],"they":[10],"can":[11,35],"be":[12,36],"embedded":[13],"a":[15,21,30,32,39,42,49,67,75],"Euclidean":[16],"space":[17,69],"which":[18],"reflects":[19],"an":[20],"priori":[22],"notion":[23],"of":[24,44],"similarity":[25],"between":[26],"them.":[27],"In":[28],"such":[29,55],"case,":[31],"text":[33],"document":[34,51],"viewed":[37],"bag-of-embedded-words":[40],"(BoEW):":[41],"set":[43],"real-valued":[45],"vectors.":[46],"We":[47,78],"propose":[48],"novel":[50],"representation":[52],"based":[53],"on":[54],"continuous":[56],"word":[57],"embeddings.":[58],"It":[59],"consists":[60],"non-linearly":[62],"mapping":[63],"the":[64,83,86,100],"word-embeddings":[65,87],"higher-dimensional":[68],"and":[70],"aggregating":[72],"them":[73],"into":[74],"document-level":[76],"representation.":[77],"report":[79],"retrieval":[80],"experiments":[81],"case":[84],"where":[85],"computed":[89],"from":[90],"standard":[91],"topic":[92,102],"models":[93],"showing":[94],"significant":[95],"improvements":[96],"with":[97],"respect":[98],"to":[99],"original":[101],"models.":[103]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}