{"id":"https://openalex.org/W3210791897","doi":"https://doi.org/10.1145/3459637.3482028","title":"IR From Bag-of-words to BERT and Beyond through Practical Experiments","display_name":"IR From Bag-of-words to BERT and Beyond through Practical Experiments","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3210791897","doi":"https://doi.org/10.1145/3459637.3482028","mag":"3210791897"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482028","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5057643560","display_name":"Craig Macdonald","orcid":"https://orcid.org/0000-0003-3143-279X"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Craig Macdonald","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018894843","display_name":"Nicola Tonellotto","orcid":"https://orcid.org/0000-0002-7427-1001"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Tonellotto","raw_affiliation_strings":["University of Pisa, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014199889","display_name":"Sean MacAvaney","orcid":"https://orcid.org/0000-0002-8914-2659"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sean MacAvaney","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4861","last_page":"4861"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9952999949455261,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9945999979972839,"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":0.8422501087188721},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6318233013153076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5818307995796204},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5724746584892273},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5448803901672363},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5396741628646851},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48969510197639465},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4706413447856903},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4677667021751404},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45653778314590454},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4412868916988373},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.4165460765361786},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.41368210315704346},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32808947563171387},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1509469747543335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8422501087188721},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6318233013153076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5818307995796204},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5724746584892273},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5448803901672363},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5396741628646851},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48969510197639465},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4706413447856903},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4677667021751404},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45653778314590454},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4412868916988373},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.4165460765361786},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.41368210315704346},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32808947563171387},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1509469747543335},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3459637.3482028","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8500000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1973435495","https://openalex.org/W2117473841","https://openalex.org/W2149427297","https://openalex.org/W2896457183","https://openalex.org/W3001344098","https://openalex.org/W3021397474","https://openalex.org/W3021779606","https://openalex.org/W3023238803","https://openalex.org/W3044997488","https://openalex.org/W3045745713","https://openalex.org/W3082274269","https://openalex.org/W3099384026","https://openalex.org/W3104914963","https://openalex.org/W3128581554","https://openalex.org/W3130740619","https://openalex.org/W3175980629","https://openalex.org/W3197464301","https://openalex.org/W3209981429"],"related_works":["https://openalex.org/W2945260553","https://openalex.org/W1563618553","https://openalex.org/W3207693618","https://openalex.org/W2966892770","https://openalex.org/W1542956019","https://openalex.org/W4308654474","https://openalex.org/W4362598702","https://openalex.org/W2901412863","https://openalex.org/W3100598124","https://openalex.org/W3123622441"],"abstract_inverted_index":{"The":[0],"task":[1],"of":[2,50,55,73,157],"adhoc":[3],"search":[4,151,166],"is":[5],"undergoing":[6],"a":[7,32,46,154],"renaissance,":[8],"sparked":[9],"by":[10,161],"advances":[11],"in":[12,153],"natural":[13],"language":[14,20,51],"processing.":[15],"In":[16,83],"particular,":[17],"pre-trained":[18],"contextualized":[19],"models":[21,42],"(such":[22],"as":[23,69,131],"BERT":[24],"and":[25,77,80,134,164],"T5)":[26],"have":[27],"consistently":[28],"shown":[29],"to":[30,37,62,94,115,121,149],"be":[31,66,119,145],"highly-effective":[33],"foundation":[34],"upon":[35],"which":[36],"build":[38,88],"ranking":[39,98],"models.":[40,58],"These":[41],"are":[43],"equipped":[44],"with":[45],"far":[47],"deeper":[48],"understanding":[49],"than":[52],"the":[53,95,138,162],"capabilities":[54],"bag-of-words":[56,107],"(BoW)":[57],"Applying":[59],"these":[60,123,143],"techniques":[61],"new":[63,150],"tasks":[64,152],"can":[65,118,144],"tricky,":[67],"however,":[68],"they":[70],"require":[71],"knowledge":[72],"deep":[74],"learning":[75],"frameworks,":[76],"significant":[78],"scripting":[79],"data":[81],"munging.":[82],"this":[84],"full-day":[85],"tutorial,":[86],"we":[87,126,140],"up":[89],"from":[90],"foundational":[91,103],"retrieval":[92],"principles":[93],"latest":[96],"neural":[97],"techniques.":[99],"We":[100,109],"first":[101],"provide":[102],"background":[104],"on":[105],"classical":[106],"methods.":[108],"then":[110],"show":[111],"how":[112,142],"feature-based":[113],"Learning":[114],"Rank":[116],"methods":[117],"used":[120],"re-rank":[122],"results.":[124],"Finally,":[125],"cover":[127],"contemporary":[128],"approaches,":[129],"such":[130],"BERT,":[132],"doc2query,":[133],"dense":[135],"retrieval.":[136],"Throughout":[137],"process,":[139],"demonstrate":[141],"easily":[146],"experimentally":[147],"applied":[148],"declarative":[155],"style":[156],"conducting":[158],"experiments":[159],"exemplified":[160],"PyTerrier":[163],"OpenNIR":[165],"toolkits.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}