{"id":"https://openalex.org/W4403577396","doi":"https://doi.org/10.1145/3627673.3679971","title":"Multi-DSI: Non-deterministic Identifier and Concept Alignment for Differentiable Search Index","display_name":"Multi-DSI: Non-deterministic Identifier and Concept Alignment for Differentiable Search Index","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403577396","doi":"https://doi.org/10.1145/3627673.3679971"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679971","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","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/A5107829861","display_name":"Y. F. Liu","orcid":"https://orcid.org/0009-0009-0394-0675"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yu-Ze Liu","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048749901","display_name":"Jyun\u2010Yu Jiang","orcid":"https://orcid.org/0000-0002-1753-8099"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jyun-Yu Jiang","raw_affiliation_strings":["Amazon Search, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Search, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210133358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071684622","display_name":"Pu\u2010Jen Cheng","orcid":"https://orcid.org/0000-0001-5892-0385"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Pu-Jen Cheng","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5107829861"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16303324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3917","last_page":"3921"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9984999895095825,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9984999895095825,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9786999821662903,"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/T11106","display_name":"Data Management and Algorithms","score":0.9513999819755554,"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/identifier","display_name":"Identifier","score":0.7151635885238647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6948005557060242},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.5940577983856201},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5282292366027832},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36995309591293335},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35665497183799744},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3293755352497101},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18848541378974915},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15278223156929016},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.05652040243148804}],"concepts":[{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.7151635885238647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6948005557060242},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5940577983856201},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5282292366027832},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36995309591293335},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35665497183799744},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3293755352497101},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18848541378974915},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15278223156929016},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.05652040243148804}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679971","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2912924812","https://openalex.org/W2981852735","https://openalex.org/W3021397474","https://openalex.org/W4221166196","https://openalex.org/W4224438163","https://openalex.org/W4288089799","https://openalex.org/W4320465836","https://openalex.org/W4385567756","https://openalex.org/W4385571319","https://openalex.org/W4387848863","https://openalex.org/W4388105019","https://openalex.org/W4393153307","https://openalex.org/W6810139940","https://openalex.org/W6850138286"],"related_works":["https://openalex.org/W4285277090","https://openalex.org/W4378651134","https://openalex.org/W4327738859","https://openalex.org/W4252684102","https://openalex.org/W2608983118","https://openalex.org/W2348722996","https://openalex.org/W2352307597","https://openalex.org/W1979633005","https://openalex.org/W2163724607","https://openalex.org/W3135403405"],"abstract_inverted_index":{"With":[0],"the":[1,31,38,44,49,56,63,66,88],"advent":[2],"of":[3,43,68,90],"generative":[4,8],"deep":[5],"learning":[6],"models,":[7],"IR":[9],"has":[10],"gained":[11],"increasing":[12],"attention.":[13],"However,":[14],"existing":[15],"methods":[16,109],"face":[17],"two":[18,100],"issues:":[19],"(1)":[20,79],"when":[21,48],"a":[22,27],"document":[23],"is":[24],"represented":[25],"by":[26,110],"single":[28],"semantic":[29,54,83],"ID,":[30],"retrieval":[32,57],"model":[33,58],"may":[34,59],"fail":[35],"to":[36,61,78,94],"capture":[37],"multifaceted":[39],"and":[40,46,85,92],"complex":[41],"content":[42,67],"document;":[45],"(2)":[47,86],"generated":[50],"training":[51],"data":[52],"exhibits":[53],"ambiguity,":[55],"struggle":[60],"distinguish":[62],"differences":[64],"in":[65],"similar":[69],"documents.":[70],"To":[71],"address":[72],"these":[73],"issues,":[74],"we":[75],"propose":[76],"Multi-DSI":[77,105],"offer":[80],"multiple":[81],"non-deterministic":[82],"identifiers":[84],"align":[87],"concepts":[89],"queries":[91],"documents":[93],"avoid":[95],"ambiguity.":[96],"Extensive":[97],"experiments":[98],"on":[99],"benchmark":[101],"datasets":[102],"demonstrate":[103],"that":[104],"significantly":[106],"outperforms":[107],"baseline":[108],"7.4%.":[111]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}