{"id":"https://openalex.org/W7167207557","doi":"https://doi.org/10.1145/3805712.3809724","title":"Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps","display_name":"Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167207557","doi":"https://doi.org/10.1145/3805712.3809724"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809724","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809724","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 49th 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://doi.org/10.1145/3805712.3809724","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139990032","display_name":"Zhichao Geng","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhichao Geng","raw_affiliation_strings":["Amazon Web Service, Shanghai, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-8100-2079","affiliations":[{"raw_affiliation_string":"Amazon Web Service, Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140002964","display_name":"Yang Yang","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Amazon Web Service, Shanghai, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-2480-3339","affiliations":[{"raw_affiliation_string":"Amazon Web Service, Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8971613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"403","last_page":"414"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2896000146865845,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2896000146865845,"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":0.1551000028848648,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.06610000133514404,"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/bridging","display_name":"Bridging (networking)","score":0.6913999915122986},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6480000019073486},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6141999959945679},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.3619000017642975},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.3427000045776367},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.3303000032901764},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.32580000162124634},{"id":"https://openalex.org/keywords/lag","display_name":"Lag","score":0.29580000042915344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7303000092506409},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6913999915122986},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6480000019073486},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6141999959945679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4925999939441681},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.47510001063346863},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.3303000032901764},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31610000133514404},{"id":"https://openalex.org/C75778745","wikidata":"https://www.wikidata.org/wiki/Q342626","display_name":"Lag","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28630000352859497},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2628999948501587}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3805712.3809724","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809724","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2607.00004","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.00004","pdf_url":"https://arxiv.org/pdf/2607.00004","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809724","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809724","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 49th 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":0.4997548460960388}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"advanced":[1,109],"foundation":[2],"models":[3,180],"like":[4,181],"ModernBERT":[5,164],"significantly":[6],"outperform":[7],"older":[8],"architectures":[9,188],"in":[10,21,154],"dense":[11,151],"retrieval,":[12],"they":[13],"surprisingly":[14],"lag":[15,198],"behind":[16],"the":[17,28,32,80,87,147,170,196],"aging":[18],"BERT-base":[19],"baseline":[20],"learned":[22],"sparse":[23],"retrieval":[24],"(LSR).":[25],"We":[26,65],"identify":[27],"root":[29],"cause":[30],"as":[31],"Vocabulary":[33,101],"Gap":[34],":":[35],"modern":[36],"tokenizers":[37],"utilize":[38],"raw,":[39],"case-sensitive":[40],"vocabularies":[41,114],"designed":[42],"for":[43],"lossless":[44],"reconstruction,":[45],"which":[46],"map":[47],"single":[48],"semantic":[49,92],"units":[50],"to":[51,111,128,139,165,186],"redundant":[52],"surface":[53],"forms,":[54],"wasting":[55],"model":[56],"capacity":[57],"on":[58,169],"morphological":[59],"noise":[60],"and":[61,132,150,183,189,213],"hindering":[62],"lexical":[63],"matching.":[64],"formalize":[66],"this":[67],"intuition":[68],"through":[69],"a":[70,104,121,175,205],"theoretical":[71],"framework,":[72],"demonstrating":[73],"that":[74,91,107,195],"appropriate":[75],"vocabulary":[76,207],"coarse-graining":[77],"can":[78],"tighten":[79],"generalization":[81],"bounds":[82],"by":[83],"reducing":[84],"complexity":[85],"of":[86],"hypothesis":[88],"class,":[89],"provided":[90],"integrity":[93],"is":[94,159,199],"preserved.":[95],"To":[96],"resolve":[97],"this,":[98],"we":[99],"propose":[100],"Transfer":[102],"(VT),":[103],"model-agnostic":[105],"framework":[106],"migrates":[108],"encoders":[110],"sparse-friendly,":[112],"normalized":[113],"with":[115,143],"minimal":[116],"computational":[117],"cost.":[118],"VT":[119,158],"utilizes":[120],"novel":[122],"Semantic":[123],"Initialization":[124],"via":[125],"spatial":[126],"topology":[127],"preserve":[129],"geometric":[130],"structure":[131],"an":[133,201],"Activation":[134],"Potential":[135],"Calibration":[136],"(APC)":[137],"mechanism":[138],"align":[140],"pre-trained":[141],"manifolds":[142],"sparsity":[144],"constraints,":[145],"preventing":[146],"dead":[148],"neuron":[149],"collapse":[152],"observed":[153],"standard":[155],"fine-tuning.":[156],"Empirically,":[157],"universally":[160],"effective:":[161],"it":[162],"enables":[163],"achieve":[166],"state-of-the-art":[167],"performance":[168,197],"BEIR":[171],"benchmark":[172],"(52.4":[173],"nDCG,":[174],"+4.7":[176],"improvement),":[177],"resuscitates":[178],"failing":[179],"RoBERTa-large,":[182],"generalizes":[184],"seamlessly":[185],"inference-free":[187],"specialized":[190],"domains.":[191],"These":[192],"results":[193],"confirm":[194],"not":[200],"architectural":[202],"deficiency":[203],"but":[204],"solvable":[206],"mismatch.":[208],"We've":[209],"released":[210],"our":[211],"code":[212],"models.":[214],"https://anonymous.4open.science/r/vocab-transfer/.":[215],"All":[216],"details":[217],"included.":[218]},"counts_by_year":[],"updated_date":"2026-07-11T05:49:48.208612","created_date":"2026-07-04T00:00:00"}