{"id":"https://openalex.org/W7225224965","doi":"https://doi.org/10.4324/9781042013173-10","title":"Tokenization, Embeddings, and Attention","display_name":"Tokenization, Embeddings, and Attention","publication_year":2026,"publication_date":"2026-11-04","ids":{"openalex":"https://openalex.org/W7225224965","doi":"https://doi.org/10.4324/9781042013173-10"},"language":"en","primary_location":{"id":"doi:10.4324/9781042013173-10","doi":"https://doi.org/10.4324/9781042013173-10","is_oa":false,"landing_page_url":"https://doi.org/10.4324/9781042013173-10","pdf_url":null,"source":{"id":"https://openalex.org/S4306463855","display_name":"Routledge eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319847","host_organization_name":"Routledge","host_organization_lineage":["https://openalex.org/P4310319847","https://openalex.org/P4310320547"],"host_organization_lineage_names":["Routledge","Taylor & Francis"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The New Perspectiva Artificialis","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W7225234641","display_name":"The New Perspectiva Artificialis"},"type":"book-chapter","is_traditional":true,"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/A5052787141","display_name":"James Hutson","orcid":"https://orcid.org/0000-0002-0578-6052","observed_orcids":["https://orcid.org/0000-0002-0578-6052"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Hutson","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0578-6052","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081877461","display_name":"Daniel Plate","orcid":"https://orcid.org/0000-0002-1238-5425","observed_orcids":["https://orcid.org/0000-0002-1238-5425"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Plate","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1238-5425","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.92638899,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"168","last_page":"190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9063000082969666,"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":0.9063000082969666,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0729999989271164,"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/T13308","display_name":"Cybernetics and Technology in Society","score":0.004000000189989805,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/tokenization","display_name":"tokenization","score":0.9570000171661377},{"id":"https://openalex.org/keywords/word-embeddings","display_name":"word embeddings","score":0.8550000190734863},{"id":"https://openalex.org/keywords/positional-encoding","display_name":"positional encoding","score":0.7440000176429749},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.7250000238418579},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.7379999756813049},{"id":"https://openalex.org/keywords/multimodal-alignment","display_name":"multimodal alignment","score":0.8809999823570251},{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.34599998593330383},{"id":"https://openalex.org/keywords/semantic-representation","display_name":"semantic representation","score":0.4189999997615814},{"id":"https://openalex.org/keywords/interface-effects","display_name":"interface effects","score":0.48399999737739563},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"text segmentation","score":0.3959999978542328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7286999821662903},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6078000068664551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5406000018119812},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.4887999892234802},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4611999988555908},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44839999079704285},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3962000012397766},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.30730000138282776},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C191399111","wikidata":"https://www.wikidata.org/wiki/Q64861","display_name":"Transitive relation","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C2780276568","wikidata":"https://www.wikidata.org/wiki/Q191928","display_name":"Polysemy","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27810001373291016},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C179420905","wikidata":"https://www.wikidata.org/wiki/Q223871","display_name":"Mediation","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4324/9781042013173-10","doi":"https://doi.org/10.4324/9781042013173-10","is_oa":false,"landing_page_url":"https://doi.org/10.4324/9781042013173-10","pdf_url":null,"source":{"id":"https://openalex.org/S4306463855","display_name":"Routledge eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319847","host_organization_name":"Routledge","host_organization_lineage":["https://openalex.org/P4310319847","https://openalex.org/P4310320547"],"host_organization_lineage_names":["Routledge","Taylor & Francis"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The New Perspectiva Artificialis","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4392788491","https://openalex.org/W6893478311","https://openalex.org/W4414490976","https://openalex.org/W7117998578","https://openalex.org/W7155172375","https://openalex.org/W6929417143","https://openalex.org/W4412888623","https://openalex.org/W7160268374","https://openalex.org/W4386081899","https://openalex.org/W4294955582"],"abstract_inverted_index":{"This":[0],"chapter":[1,51,111,183],"examines":[2,136],"how":[3,65],"transformer-based":[4],"language":[5,43,73],"systems":[6],"construct":[7],"a":[8,33,75,116,119],"semantic":[9,89,121],"field":[10],"from":[11,190,203],"textual":[12,95],"materials":[13],"that":[14,44,185],"have":[15],"already":[16],"been":[17],"made":[18],"available":[19],"as":[20,32,38,74,82,115,138],"corpus":[21,87],"and":[22,61,88,108,132,143,162,180,198],"training":[23],"substrate.":[24],"It":[25,134],"begins":[26],"with":[27],"tokenization,":[28],"treating":[29],"segmentation":[30],"not":[31],"neutral":[34],"preprocessing":[35],"detail":[36],"but":[37],"an":[39],"operational":[40],"partitioning":[41],"of":[42,56,104,193],"allows":[45],"text":[46],"to":[47,155,172],"become":[48],"computable.":[49],"The":[50,110,149,182],"then":[52,135],"follows":[53],"the":[54,83,186],"organization":[55],"sequence":[57],"through":[58,128],"positional":[59],"encoding":[60],"related":[62],"mechanisms,":[63],"showing":[64],"models":[66],"preserve":[67],"relations":[68,103],"among":[69],"tokens":[70],"without":[71],"reading":[72],"human":[76],"reader":[77],"does.":[78],"Embeddings":[79],"are":[80,164],"presented":[81],"crucial":[84],"hinge":[85],"between":[86],"geometry,":[90],"since":[91],"they":[92],"transform":[93],"discrete":[94],"units":[96],"into":[97,166],"vectors":[98],"whose":[99],"positions":[100],"encode":[101],"learned":[102],"use,":[105],"similarity,":[106],"context,":[107],"association.":[109],"develops":[112],"latent":[113],"space":[114],"relational":[117],"topography,":[118],"produced":[120],"world-space":[122],"in":[123,175],"which":[124],"meaning":[125],"becomes":[126],"navigable":[127],"distance,":[129],"direction,":[130],"clustering,":[131],"transformation.":[133],"attention":[137],"contextual":[139],"routing,":[140,197],"weighted":[141],"relation,":[142],"iterative":[144],"refinement":[145],"across":[146],"transformer":[147],"layers.":[148],"later":[150],"sections":[151],"extend":[152],"this":[153],"account":[154],"multimodal":[156],"alignment,":[157],"where":[158],"language,":[159],"image,":[160],"sound,":[161],"action":[163],"brought":[165],"shared":[167],"representational":[168],"systems,":[169],"before":[170],"turning":[171],"interface":[173,199],"effects":[174],"search,":[176],"summarization,":[177],"co-writing,":[178],"dialogue,":[179],"analysis.":[181],"argues":[184],"algorithmic":[187],"voice":[188],"arises":[189],"layered":[191],"procedures":[192],"segmentation,":[194],"positioning,":[195],"embedding,":[196],"mediation":[200],"rather":[201],"than":[202],"disembodied":[204],"fluency":[205],"or":[206],"autonomous":[207],"cognition.":[208]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-05T00:00:00"}