{"id":"https://openalex.org/W3174183013","doi":"https://doi.org/10.1162/coli_r_00410","title":"Embeddings in Natural Language Processing: Theory and Advances in Vector Representations of Meaning","display_name":"Embeddings in Natural Language Processing: Theory and Advances in Vector Representations of Meaning","publication_year":2021,"publication_date":"2021-06-30","ids":{"openalex":"https://openalex.org/W3174183013","doi":"https://doi.org/10.1162/coli_r_00410","mag":"3174183013"},"language":"en","primary_location":{"id":"doi:10.1162/coli_r_00410","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_r_00410","pdf_url":"https://direct.mit.edu/coli/article-pdf/47/3/699/1971846/coli_r_00410.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/coli/article-pdf/47/3/699/1971846/coli_r_00410.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035151979","display_name":"Marcos Garc\u00eda","orcid":"https://orcid.org/0000-0002-6557-0210"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Marcos Garcia","raw_affiliation_strings":["CiTIUS, University of Santiago de Compostela"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CiTIUS, University of Santiago de Compostela","institution_ids":["https://openalex.org/I200284239"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5035151979"],"corresponding_institution_ids":["https://openalex.org/I200284239"],"apc_list":null,"apc_paid":null,"fwci":1.1193,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82162684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"47","issue":"3","first_page":"699","last_page":"701"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8737000226974487,"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":0.8737000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7738803625106812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6677430868148804},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5976315140724182},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.5335640907287598},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.49138203263282776},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.4820874035358429},{"id":"https://openalex.org/keywords/principle-of-compositionality","display_name":"Principle of compositionality","score":0.4454876184463501},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4446926414966583},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.434567928314209},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42626050114631653},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41977059841156006},{"id":"https://openalex.org/keywords/distributional-semantics","display_name":"Distributional semantics","score":0.41347184777259827},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3572460114955902},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.34879565238952637},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.13010981678962708},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08863496780395508},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08810776472091675}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738803625106812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6677430868148804},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5976315140724182},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.5335640907287598},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.49138203263282776},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.4820874035358429},{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.4454876184463501},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4446926414966583},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.434567928314209},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42626050114631653},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41977059841156006},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.41347184777259827},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3572460114955902},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.34879565238952637},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.13010981678962708},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08863496780395508},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08810776472091675},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/coli_r_00410","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_r_00410","pdf_url":"https://direct.mit.edu/coli/article-pdf/47/3/699/1971846/coli_r_00410.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:049ff6d4787148aabc6ee0fcedfe80dd","is_oa":false,"landing_page_url":"https://doaj.org/article/049ff6d4787148aabc6ee0fcedfe80dd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 47, Iss 3, Pp 699-701 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_r_00410","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_r_00410","pdf_url":"https://direct.mit.edu/coli/article-pdf/47/3/699/1971846/coli_r_00410.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2608109911","https://openalex.org/W1715304901","https://openalex.org/W2912764446","https://openalex.org/W2784926331","https://openalex.org/W84019336","https://openalex.org/W2170770969","https://openalex.org/W1847856012","https://openalex.org/W2572858686","https://openalex.org/W1583123819","https://openalex.org/W2260018915"],"abstract_inverted_index":{"Word":[0],"vector":[1,45,109,157,288,382,396,461,508,567,744,874,956],"representations":[2,117,178,201,289,745,802,875],"have":[3,19,152],"a":[4,98,123,190,217,232,305,354,404,646,740,902],"long":[5],"tradition":[6],"in":[7,52,68,83,108,196,339,565,710,831,850,887,948,994],"several":[8,270,687,836],"research":[9,585],"fields,":[10],"such":[11,486,689,713,749],"as":[12,80,350,487,499,501,690,714,750,764,766],"cognitive":[13],"science":[14],"or":[15,536,693,790],"computational":[16,53,197],"linguistics.":[17],"They":[18,159],"been":[20,49,153],"used":[21,51,154],"to":[22,55,126,155,215,231,282,325,357,457,515,529,539,595,601,651,706,827,854,882,926,943,989,996],"represent":[23,56,645],"the":[24,40,57,63,71,104,132,141,145,164,185,220,238,241,243,251,254,259,277,291,318,327,330,379,389,393,431,444,447,452,512,526,566,575,621,625,629,662,676,694,701,727,730,756,767,775,804,810,844,847,851,857,869,914,918,933,937,953,970,974],"meaning":[25],"of":[26,29,59,65,73,103,129,163,168,174,209,235,258,262,287,329,360,372,378,395,407,418,427,451,468,506,579,612,624,636,639,686,729,743,746,758,769,778,800,806,815,824,860,868,872,905,908,952,955,973,979],"various":[27,704],"units":[28],"natural":[30,60,787],"languages,":[31],"including,":[32],"among":[33],"others,":[34],"words,":[35],"phrases,":[36],"and":[37,94,100,106,118,131,134,149,171,179,202,225,240,264,300,311,322,365,392,415,417,436,477,481,489,496,503,518,559,606,619,628,674,680,700,717,752,761,771,798,821,876,892,917,922,976,992],"sentences.":[38],"Before":[39],"deep":[41,428,980],"learning":[42,86,211,777,981],"tsunami,":[43],"count-based":[44,475],"space":[46,383,397,957],"models":[47,110,182,341,384,485,654,666,709,817,941,958],"had":[48],"successfully":[50],"linguistics":[54],"semantics":[58],"languages.":[61],"However,":[62],"rise":[64],"neural":[66,266,544,670,735,965],"networks":[67,671],"NLP":[69,263,412,852],"popularized":[70],"use":[72,707,822],"word":[74,469,581,647,657,801,832],"embeddings,":[75,295,297,299,532,582,640,833],"which":[76,227,438,562,583,609],"are":[77,552,794,803],"now":[78],"applied":[79],"pre-trained":[81],"vectors":[82],"most":[84,146,165,453,919,938],"machine":[85,210,791],"architectures.This":[87],"book,":[88],"written":[89],"by":[90,304,402,573,648,734,835,865,969],"Mohammad":[91],"Taher":[92],"Pilehvar":[93],"Jose":[95],"Camacho-Collados,":[96],"provides":[97],"comprehensive":[99],"easy-to-read":[101],"review":[102,467],"theory":[105],"advances":[107,167],"for":[111,193,199,342,385,411,655,774,818,878,910,983],"NLP,":[112,361,911,984],"focusing":[113],"specially":[114],"on":[115,184,542,586,668,675,786,896,913,963],"semantic":[116,200,386],"their":[119,884],"applications.":[120],"It":[121,471,632,754],"is":[122,189,245,464,697,987],"great":[124],"introduction":[125,356,406],"different":[127,285,370,474,906],"types":[128,286,371,638,907],"embeddings":[130,498,520,551,618,909],"background":[133],"motivations":[135],"behind":[136],"them.":[137],"In":[138,250,659],"this":[139,169,188,660,899],"sense,":[140],"authors":[142,255,448,663,702,811,845],"adequately":[143],"present":[144,284,449,664,812,830],"relevant":[147,454],"concepts":[148,271,437,916],"approaches":[150,476,505,548,594,608,705,961],"that":[151,272,644],"build":[156,458,516,530,596],"representations.":[158,588],"also":[160,493,698,721,795,935],"keep":[161],"track":[162],"recent":[166,939],"vibrant":[170],"fast-evolving":[172],"area":[173],"research,":[175],"discussing":[176,269],"cross-lingual":[177,507],"current":[180,652,873,960],"language":[181,420,653,736,788,999],"based":[183,541,667,962],"Transformer.":[186],"Therefore,":[187],"useful":[191,275,924],"book":[192,221,244,319,863,900,934],"researchers":[194],"interested":[195],"methods":[198,321,514,540,561,600,643,837,982],"artificial":[203,265,343,819,964],"intelligence.":[204,344],"Although":[205],"some":[206,257,358,408,450,681,723,813,867],"basic":[207],"knowledge":[208,455,557],"may":[212],"be":[213,274,348,440],"necessary":[214,988],"follow":[216],"few":[218],"topics,":[219],"includes":[222,320,633,923],"clear":[223],"illustrations":[224],"explanations,":[226],"make":[228],"it":[229,423,492,524,946],"accessible":[230],"wide":[233],"range":[234],"readers.Apart":[236],"from":[237,363,366,521,533,556,604,641],"preface":[239],"conclusions,":[242],"organized":[246],"into":[247,929],"eight":[248],"chapters.":[249],"first":[252,472],"two,":[253],"introduce":[256],"core":[260],"ideas":[261],"networks,":[267],"respectively,":[268],"will":[273,439],"throughout":[276],"book.":[278,445],"Then,":[279,422,546],"Chapters":[280],"3":[281,463],"6":[283,615],"at":[290,839],"lexical":[292,613],"level":[293],"(word":[294],"graph":[296,543],"sense":[298,587,597],"contextualized":[301,617,656,665,940],"embeddings),":[302],"followed":[303,834],"brief":[306,355,741],"chapter":[307,346,380,400,570,590],"(7)":[308],"about":[309],"sentence":[310,779],"document":[312],"embeddings.":[313,331,470,780],"For":[314],"each":[315],"specific":[316,930],"topic,":[317],"data":[323],"sets":[324],"assess":[326],"quality":[328],"Finally,":[332,446,719],"Chapter":[333,807],"8":[334],"raises":[335],"ethical":[336],"issues":[337],"involved":[338],"data-driven":[340,816],"Each":[345],"can":[347],"summarized":[349],"follows.Chapter":[351],"1":[352],"makes":[353],"challenges":[359],"both":[362],"understanding":[364],"generation":[367],"perspectives,":[368],"including":[369],"linguistic":[373,409,731],"ambiguity.":[374],"The":[375,683],"main":[376,593,622],"part":[377],"introduces":[381],"representation,":[387],"presenting":[388,430,574],"distributional":[390],"hypothesis":[391],"evolution":[394],"models.The":[398,862],"second":[399],"starts":[401,572],"giving":[403],"quick":[405],"fundamentals":[410],"(syntax,":[413],"morphology,":[414],"semantics)":[416],"statistical":[419],"models.":[421],"gives":[424],"an":[425,465,634,894,949],"overview":[426,635],"learning,":[429],"fundamental":[432],"differences":[433],"between":[434],"architectures,":[435],"referred":[441],"along":[442],"with":[443,893,959],"resources":[456],"semantically":[459],"richer":[460],"representations.Chapter":[462,509],"extensive":[466],"presents":[473,525,755],"dimensionality":[478],"reduction":[479],"techniques":[480],"then":[482],"discusses":[483,591,936],"predictive":[484],"Word2vec":[488],"GloVe.":[490],"Additionally,":[491],"describes":[494,620],"character-based":[495],"knowledge-based":[497,607],"well":[500,765],"supervised":[502,782],"unsupervised":[504,560,599,776],"4":[510],"illustrates":[511],"principal":[513],"node":[517,531],"relation":[519,550],"graphs.":[522],"First,":[523],"key":[527],"strategies":[528,783],"matrix":[534],"factorization":[535],"random":[537],"walks":[538],"networks.":[545,966],"two":[547,592],"regarding":[549,726],"presented:":[553],"those":[554,841],"built":[555],"graphs,":[558],"exploit":[563],"regularities":[564],"space.The":[568],"next":[569],"(5)":[571],"Meaning":[576],"Conflation":[577],"Deficiency":[578],"static":[580],"motivates":[584],"This":[589],"embeddings:":[598],"induce":[602],"senses":[603],"corpora,":[605],"take":[610],"advantage":[611],"resources.Chapter":[614],"addresses":[616],"properties":[623,732],"Transformer":[626,677],"architecture":[627],"self-attention":[630],"mechanism.":[631],"these":[637,708,861],"early":[642],"its":[649,762,772],"context,":[650],"representation.":[658],"respect,":[661],"recurrent":[669],"(e.g.,":[672,784],"ELMo),":[673],"(GPT,":[678],"BERT,":[679],"derivatives).":[682],"potential":[684],"impact":[685,859],"parameters,":[688],"subword":[691],"tokenization":[692],"training":[695,785],"objectives,":[696],"explained,":[699],"discuss":[703],"downstream":[711],"tasks,":[712],"feature":[715],"extraction":[716],"finetuning.":[718],"they":[720],"summarize":[722],"interesting":[724],"insights":[725],"exploration":[728],"encoded":[733],"models.Chapter":[737],"7":[738],"comprises":[739],"sketch":[742],"longer":[747],"units,":[748],"sentences":[751],"documents.":[753],"bag":[757],"words":[759],"approach":[760],"limitations":[763],"concept":[768],"compositionality":[770],"significance":[773],"Some":[781],"inference":[789],"translation":[792],"datasets)":[793],"discussed.Ethical":[796],"aspects":[797],"biases":[799,829],"focus":[805],"8.":[808],"Here,":[809],"risks":[814],"intelligence":[820],"examples":[823],"gender":[825],"stereotypes":[826],"show":[828],"aimed":[838],"reducing":[840],"biases.":[842],"Overall,":[843],"emphasize":[846],"growing":[848],"interest":[849],"community":[853],"critically":[855],"analyze":[856],"social":[858],"concludes":[864],"highlighting":[866],"major":[870],"achievements":[871],"calling":[877],"more":[879],"rigorous":[880],"evaluations":[881],"measure":[883],"progress,":[885],"especially":[886],"languages":[888],"other":[889],"than":[890],"English,":[891],"eye":[895],"interpretability.In":[897],"summary,":[898],"brings":[901],"high-level":[903],"synthesis":[904],"focused":[912],"general":[915],"established":[920],"techniques,":[921],"pointers":[925],"delve":[927],"deeper":[928],"topics.":[931],"As":[932,967],"(up":[942],"November":[944],"2020),":[945],"results":[947],"attractive":[950],"combination":[951],"foundations":[954],"suggested":[968],"authors,":[971],"because":[972],"explosion":[975],"rapid":[977],"development":[978],"maybe":[985],"\u201cit":[986],"step":[990],"back":[991],"rethink":[993],"order":[995],"achieve":[997],"true":[998],"understanding.\u201d":[1000]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-19T21:40:30.786675","created_date":"2025-10-10T00:00:00"}