{"id":"https://openalex.org/W4416958355","doi":"https://doi.org/10.1145/3767695.3769498","title":"C2T-ID: Converting Semantic Codebooks to Textual Document Identifiers for Generative Search","display_name":"C2T-ID: Converting Semantic Codebooks to Textual Document Identifiers for Generative Search","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4416958355","doi":"https://doi.org/10.1145/3767695.3769498"},"language":null,"primary_location":{"id":"doi:10.1145/3767695.3769498","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769498","pdf_url":null,"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 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767695.3769498","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yingchen Zhang","orcid":"https://orcid.org/0009-0003-3979-6069"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yingchen Zhang","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-3979-6069","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009898523","display_name":"Ruqing Zhang","orcid":"https://orcid.org/0000-0003-4294-2541"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruqing Zhang","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4294-2541","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088621320","display_name":"Jiafeng Guo","orcid":"https://orcid.org/0000-0002-9509-8674"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafeng Guo","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9509-8674","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013331292","display_name":"W. Peng","orcid":"https://orcid.org/0000-0003-2392-4946"},"institutions":[{"id":"https://openalex.org/I4210144142","display_name":"Hangzhou Institute of Applied Acoustics","ror":"https://ror.org/0473ary24","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Peng","raw_affiliation_strings":["Researcher, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2392-4946","affiliations":[{"raw_affiliation_string":"Researcher, Hangzhou, China","institution_ids":["https://openalex.org/I4210144142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039770442","display_name":"S. X. Li","orcid":"https://orcid.org/0000-0002-2124-953X"},"institutions":[{"id":"https://openalex.org/I4210144142","display_name":"Hangzhou Institute of Applied Acoustics","ror":"https://ror.org/0473ary24","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sen Li","raw_affiliation_strings":["Researcher, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2124-953X","affiliations":[{"raw_affiliation_string":"Researcher, Hangzhou, China","institution_ids":["https://openalex.org/I4210144142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087662735","display_name":"Fuyu Lv","orcid":"https://orcid.org/0000-0001-5918-093X"},"institutions":[{"id":"https://openalex.org/I4210144142","display_name":"Hangzhou Institute of Applied Acoustics","ror":"https://ror.org/0473ary24","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuyu Lv","raw_affiliation_strings":["Researcher, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5918-093X","affiliations":[{"raw_affiliation_string":"Researcher, Hangzhou, China","institution_ids":["https://openalex.org/I4210144142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029998682","display_name":"Xueqi Cheng","orcid":"https://orcid.org/0000-0002-5201-8195"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5201-8195","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49451602,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"331","last_page":"336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.444599986076355,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.444599986076355,"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/T10028","display_name":"Topic Modeling","score":0.26019999384880066,"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":0.0348999984562397,"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/semantic-compression","display_name":"Semantic compression","score":0.7206000089645386},{"id":"https://openalex.org/keywords/semantic-search","display_name":"Semantic search","score":0.5866000056266785},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5151000022888184},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.492900013923645},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.4406999945640564},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.41339999437332153},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4120999872684479},{"id":"https://openalex.org/keywords/semantic-grid","display_name":"Semantic grid","score":0.35850000381469727},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.34209999442100525},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.33649998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8399999737739563},{"id":"https://openalex.org/C202708506","wikidata":"https://www.wikidata.org/wiki/Q7449050","display_name":"Semantic compression","level":5,"score":0.7206000089645386},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.5866000056266785},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5338000059127808},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5151000022888184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.511900007724762},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.492900013923645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46399998664855957},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.4406999945640564},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C103692084","wikidata":"https://www.wikidata.org/wiki/Q1765824","display_name":"Semantic grid","level":3,"score":0.35850000381469727},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.31369999051094055},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.30059999227523804},{"id":"https://openalex.org/C110903229","wikidata":"https://www.wikidata.org/wiki/Q7449064","display_name":"Semantic integration","level":4,"score":0.29580000042915344},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2854999899864197},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C174252522","wikidata":"https://www.wikidata.org/wiki/Q3816772","display_name":"Natural language user interface","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C173862523","wikidata":"https://www.wikidata.org/wiki/Q5421270","display_name":"Explicit semantic analysis","level":5,"score":0.2565999925136566},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C37926939","wikidata":"https://www.wikidata.org/wiki/Q7449061","display_name":"Semantic equivalence","level":4,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3767695.3769498","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769498","pdf_url":null,"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 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3767695.3769498","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769498","pdf_url":null,"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 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2912924812","https://openalex.org/W3021397474","https://openalex.org/W3034999214","https://openalex.org/W4223512675","https://openalex.org/W4252076394","https://openalex.org/W4292215729","https://openalex.org/W4367680667","https://openalex.org/W4386302269","https://openalex.org/W4393096553","https://openalex.org/W4393153307","https://openalex.org/W4396723267","https://openalex.org/W4400528921"],"related_works":[],"abstract_inverted_index":{"Designing":[0],"document":[1],"identifiers":[2,43],"(docids)":[3],"that":[4,130],"carry":[5],"rich":[6],"semantic":[7,31,61,84,112,135,146],"information":[8],"while":[9],"maintaining":[10],"tractable":[11],"search":[12,128,149],"spaces":[13],"is":[14],"a":[15,29],"important":[16],"challenge":[17],"in":[18,144],"generative":[19],"retrieval":[20],"(GR).":[21],"Popular":[22],"codebook":[23],"methods":[24],"address":[25],"this":[26,77],"by":[27],"building":[28],"hierarchical":[30,88],"tree":[32],"and":[33,96,107,125,137],"constraining":[34],"generation":[35],"to":[36,72],"its":[37,103,142],"child":[38],"nodes,":[39],"yet":[40],"their":[41],"numeric":[42,100],"cannot":[44],"leverage":[45],"the":[46,65,69,117],"large":[47],"language":[48,52],"model's":[49],"pretrained":[50],"natural":[51],"understanding.":[53],"Conversely,":[54],"using":[55],"text":[56],"as":[57],"docid":[58,86,139],"provides":[59],"more":[60],"expressivity":[62],"but":[63],"inflates":[64],"decoding":[66],"space,":[67],"making":[68],"system":[70],"brittle":[71],"early-step":[73],"errors.":[74],"To":[75],"resolve":[76],"trade-off,":[78],"we":[79],"propose":[80],"C2T-ID:(i)":[81],"first":[82],"construct":[83],"numerical":[85],"via":[87],"clustering;":[89],"(ii)":[90],"then":[91],"extract":[92],"high-frequency":[93],"metadata":[94],"keywords":[95],"iteratively":[97],"replace":[98],"each":[99],"label":[101],"with":[102,148],"cluster's":[104],"top-K":[105],"keywords;":[106],"(iii)":[108],"an":[109],"optional":[110],"two-level":[111],"smoothing":[113],"step":[114],"further":[115],"enhances":[116],"fluency":[118],"of":[119],"C2T-ID.":[120],"Experiments":[121],"on":[122],"Natural":[123],"Questions":[124],"Taobao's":[126],"product":[127],"demonstrate":[129],"C2T-ID":[131],"significantly":[132],"outperforms":[133],"atomic,":[134],"codebook,":[136],"pure-text":[138],"baselines,":[140],"demonstrating":[141],"effectiveness":[143],"balancing":[145],"expressiveness":[147],"space":[150],"constraints.":[151]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-03T00:00:00"}