{"id":"https://openalex.org/W2119953525","doi":"https://doi.org/10.1145/1394251.1394271","title":"Beyond bags of words","display_name":"Beyond bags of words","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2119953525","doi":"https://doi.org/10.1145/1394251.1394271","mag":"2119953525"},"language":"en","primary_location":{"id":"doi:10.1145/1394251.1394271","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1394251.1394271","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGIR Forum","raw_type":"journal-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/A5000115067","display_name":"Donald Metzler","orcid":"https://orcid.org/0000-0003-4276-6269"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Donald Metzler","raw_affiliation_strings":["University of Massachusetts, Amherst, MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5000115067"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":7.4367,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.96926083,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"42","issue":"1","first_page":"77","last_page":"77"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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":0.9987000226974487,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9984999895095825,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9197760820388794},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6926669478416443},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6498533487319946},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.5283606648445129},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5276072025299072},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4831201732158661},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4736933708190918},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4691767990589142},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41562527418136597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3608939051628113},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35119569301605225},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07757478952407837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9197760820388794},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6926669478416443},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6498533487319946},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.5283606648445129},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5276072025299072},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4831201732158661},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4736933708190918},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4691767990589142},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41562527418136597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3608939051628113},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35119569301605225},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07757478952407837},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1394251.1394271","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1394251.1394271","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGIR Forum","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":118,"referenced_works":["https://openalex.org/W11620817","https://openalex.org/W63837240","https://openalex.org/W66185676","https://openalex.org/W132343450","https://openalex.org/W192438917","https://openalex.org/W1482214997","https://openalex.org/W1484654248","https://openalex.org/W1499624045","https://openalex.org/W1501242736","https://openalex.org/W1503333931","https://openalex.org/W1518491582","https://openalex.org/W1547701650","https://openalex.org/W1555168537","https://openalex.org/W1555286071","https://openalex.org/W1591377317","https://openalex.org/W1646006088","https://openalex.org/W1880262756","https://openalex.org/W1928657940","https://openalex.org/W1964348731","https://openalex.org/W1965647483","https://openalex.org/W1966880694","https://openalex.org/W1971987737","https://openalex.org/W1973520416","https://openalex.org/W1978394996","https://openalex.org/W1978988171","https://openalex.org/W1989468977","https://openalex.org/W1994960885","https://openalex.org/W2002306339","https://openalex.org/W2007280555","https://openalex.org/W2013469094","https://openalex.org/W2014415866","https://openalex.org/W2015518873","https://openalex.org/W2020237802","https://openalex.org/W2024932032","https://openalex.org/W2026937586","https://openalex.org/W2027445772","https://openalex.org/W2028709054","https://openalex.org/W2030603245","https://openalex.org/W2030760474","https://openalex.org/W2035512259","https://openalex.org/W2036448375","https://openalex.org/W2039933790","https://openalex.org/W2040337753","https://openalex.org/W2042980227","https://openalex.org/W2043909051","https://openalex.org/W2047221353","https://openalex.org/W2048045485","https://openalex.org/W2049720982","https://openalex.org/W2055438657","https://openalex.org/W2062270497","https://openalex.org/W2065721358","https://openalex.org/W2066636486","https://openalex.org/W2067802667","https://openalex.org/W2068905009","https://openalex.org/W2069564398","https://openalex.org/W2070507812","https://openalex.org/W2070740689","https://openalex.org/W2070771761","https://openalex.org/W2078396654","https://openalex.org/W2078875869","https://openalex.org/W2081079967","https://openalex.org/W2083745421","https://openalex.org/W2084334506","https://openalex.org/W2085030399","https://openalex.org/W2086511124","https://openalex.org/W2087663869","https://openalex.org/W2092682660","https://openalex.org/W2093390569","https://openalex.org/W2096623622","https://openalex.org/W2096937925","https://openalex.org/W2099435855","https://openalex.org/W2099580784","https://openalex.org/W2099871636","https://openalex.org/W2100506586","https://openalex.org/W2105157020","https://openalex.org/W2107743791","https://openalex.org/W2112971401","https://openalex.org/W2114900318","https://openalex.org/W2123545015","https://openalex.org/W2124525949","https://openalex.org/W2125493259","https://openalex.org/W2125771191","https://openalex.org/W2127176025","https://openalex.org/W2128877075","https://openalex.org/W2129971563","https://openalex.org/W2130395434","https://openalex.org/W2131367701","https://openalex.org/W2132827946","https://openalex.org/W2136542423","https://openalex.org/W2136583886","https://openalex.org/W2136729221","https://openalex.org/W2138621811","https://openalex.org/W2139193890","https://openalex.org/W2139201316","https://openalex.org/W2139212933","https://openalex.org/W2143331230","https://openalex.org/W2145802548","https://openalex.org/W2147152072","https://openalex.org/W2152314154","https://openalex.org/W2152784831","https://openalex.org/W2153927559","https://openalex.org/W2156037541","https://openalex.org/W2158201212","https://openalex.org/W2160825952","https://openalex.org/W2160842254","https://openalex.org/W2160885631","https://openalex.org/W2162697159","https://openalex.org/W2162746367","https://openalex.org/W2163166770","https://openalex.org/W2164547069","https://openalex.org/W2165718308","https://openalex.org/W2166706824","https://openalex.org/W2169213601","https://openalex.org/W2421218773","https://openalex.org/W2432517183","https://openalex.org/W2494048233","https://openalex.org/W2496948131","https://openalex.org/W2916723970"],"related_works":["https://openalex.org/W2384888906","https://openalex.org/W2144190808","https://openalex.org/W2376314740","https://openalex.org/W2366644548","https://openalex.org/W2357241418","https://openalex.org/W2115485936","https://openalex.org/W3107474891","https://openalex.org/W2153015554","https://openalex.org/W2103338134","https://openalex.org/W2757897825"],"abstract_inverted_index":{"Current":[0],"state":[1],"of":[2,14,40,67,86,98,125],"the":[3,65,79,96,107],"art":[4],"information":[5,53,126],"retrieval":[6,34,54,127,133],"models":[7],"treat":[8],"documents":[9],"and":[10,42,88,115,134],"queries":[11],"as":[12,130],"bags":[13],"words.":[15],"There":[16],"have":[17,29],"been":[18],"many":[19],"attempts":[20],"to":[21,75,91],"go":[22],"beyond":[23,64],"this":[24,103],"simple":[25],"representation.":[26],"Unfortunately,":[27],"few":[28],"shown":[30],"consistent":[31],"improvements":[32],"in":[33],"effectiveness":[35],"across":[36],"a":[37,48,84,99,123],"wide":[38],"range":[39],"tasks":[41],"data":[43],"sets.":[44],"Here,":[45],"we":[46,105],"propose":[47],"new":[49],"statistical":[50],"model":[51,62],"for":[52,83],"based":[55],"on":[56],"Markov":[57],"random":[58],"fields.":[59],"The":[60],"proposed":[61],"goes":[63],"bag":[66],"words":[68],"assumption":[69],"by":[70],"allowing":[71],"dependencies":[72],"between":[73],"terms":[74],"be":[76,92],"incorporated":[77],"into":[78],"model.":[80,101],"This":[81],"allows":[82],"variety":[85],"textual":[87],"non-textual":[89],"features":[90],"easily":[93],"combined":[94],"under":[95],"umbrella":[97],"single":[100],"Within":[102],"framework,":[104],"explore":[106],"theoretical":[108],"issues":[109],"involved,":[110],"parameter":[111],"estimation,":[112],"feature":[113],"selection,":[114],"query":[116],"expansion.":[117],"We":[118],"give":[119],"experimental":[120],"results":[121],"from":[122],"number":[124],"tasks,":[128],"such":[129],"ad":[131],"hoc":[132],"web":[135],"search.":[136]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}