{"id":"https://openalex.org/W4376166966","doi":"https://doi.org/10.1145/3539618.3592080","title":"Unsupervised Dense Retrieval Training with Web Anchors","display_name":"Unsupervised Dense Retrieval Training with Web Anchors","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4376166966","doi":"https://doi.org/10.1145/3539618.3592080"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3592080","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3592080","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539618.3592080","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3539618.3592080","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085030899","display_name":"Yiqing Xie","orcid":"https://orcid.org/0000-0002-1668-0376"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yiqing Xie","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441089","display_name":"Xiao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Liu","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006340382","display_name":"Chenyan Xiong","orcid":"https://orcid.org/0000-0002-0392-4183"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenyan Xiong","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085030899"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.174,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53369144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2476","last_page":"2480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"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":0.859840989112854},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7583045959472656},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5902806520462036},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5675328969955444},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5191042423248291},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.4887263774871826},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.47665101289749146},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43993180990219116},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.4345400333404541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4335043430328369},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.24155193567276},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.23540863394737244},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21643918752670288},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.13685762882232666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.859840989112854},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7583045959472656},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5902806520462036},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5675328969955444},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5191042423248291},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.4887263774871826},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.47665101289749146},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43993180990219116},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.4345400333404541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4335043430328369},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.24155193567276},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.23540863394737244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21643918752670288},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.13685762882232666},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3539618.3592080","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3592080","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539618.3592080","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.05834","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.05834","pdf_url":"https://arxiv.org/pdf/2305.05834","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3539618.3592080","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3592080","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539618.3592080","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4376166966.pdf","grobid_xml":"https://content.openalex.org/works/W4376166966.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W105492840","https://openalex.org/W1489893579","https://openalex.org/W2091808810","https://openalex.org/W2111713978","https://openalex.org/W2136189984","https://openalex.org/W2147152072","https://openalex.org/W2171710828","https://openalex.org/W2595551253","https://openalex.org/W2896457183","https://openalex.org/W2951434086","https://openalex.org/W2951534261","https://openalex.org/W2970557265","https://openalex.org/W2991044292","https://openalex.org/W3004203025","https://openalex.org/W3098417575","https://openalex.org/W3099700870","https://openalex.org/W3118668786","https://openalex.org/W3131870090","https://openalex.org/W3188983256","https://openalex.org/W4221153690","https://openalex.org/W4233566471","https://openalex.org/W4252076394","https://openalex.org/W4284669679","https://openalex.org/W4286905174","https://openalex.org/W4288072953","https://openalex.org/W4288089799","https://openalex.org/W4307695992","https://openalex.org/W4310742926","https://openalex.org/W4312046631","https://openalex.org/W4320813768"],"related_works":["https://openalex.org/W4379381520","https://openalex.org/W4387073571","https://openalex.org/W2354327071","https://openalex.org/W1610765524","https://openalex.org/W1991385847","https://openalex.org/W2124561181","https://openalex.org/W2096385255","https://openalex.org/W2034972471","https://openalex.org/W2156171684","https://openalex.org/W1968898749"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,47,80],"present":[4,81],"an":[5,49],"unsupervised":[6,50,107],"retrieval":[7,109],"method":[8,124],"with":[9,54],"contrastive":[10,56],"learning":[11,57],"on":[12,44,106,118],"web":[13],"anchors.":[14],"The":[15,120],"anchor":[16,62],"text":[17,63],"describes":[18],"the":[19,25,61,65,139],"content":[20],"that":[21,34,59,90,101,138,147],"is":[22,125,144],"referenced":[23],"from":[24,40],"linked":[26,66],"page.":[27],"This":[28],"shows":[29],"similarities":[30],"to":[31,36,86,146],"search":[32,97,129,149],"queries":[33],"aim":[35],"retrieve":[37],"pertinent":[38],"information":[39,95],"relevant":[41],"documents.":[42],"Based":[43],"their":[45],"commonalities,":[46],"train":[48],"dense":[51,108],"retriever,":[52],"Anchor-DR,":[53],"a":[55,82,111],"task":[58],"matches":[60],"and":[64,130],"document.":[67],"To":[68],"filter":[69],"out":[70],"uninformative":[71],"anchors":[72,89],"(such":[73],"as":[74,96],"\"homepage\"":[75],"or":[76],"other":[77],"functional":[78],"anchors),":[79],"novel":[83],"filtering":[84],"technique":[85],"only":[87],"select":[88],"contain":[91],"similar":[92,145],"types":[93],"of":[94,122,141,148],"queries.":[98],"Experiments":[99],"show":[100],"Anchor-DR":[102],"outperforms":[103],"state-of-the-art":[104],"methods":[105],"by":[110,115],"large":[112],"margin":[113],"(e.g.,":[114],"5.3%":[116],"NDCG@10":[117],"MSMARCO).":[119],"gain":[121],"our":[123],"especially":[126],"significant":[127],"for":[128],"question":[131],"answering":[132],"tasks.":[133],"Our":[134],"analysis":[135],"further":[136],"reveals":[137],"pattern":[140],"anchor-document":[142],"pairs":[143],"query-document":[150],"pairs.":[151],"Code":[152],"available":[153],"at":[154],"https://github.com/Veronicium/AnchorDR.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}