{"id":"https://openalex.org/W3041591073","doi":"https://doi.org/10.1017/s1351324920000297","title":"Towards syntax-aware token embeddings","display_name":"Towards syntax-aware token embeddings","publication_year":2020,"publication_date":"2020-07-08","ids":{"openalex":"https://openalex.org/W3041591073","doi":"https://doi.org/10.1017/s1351324920000297","mag":"3041591073"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324920000297","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324920000297","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-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/A5081413017","display_name":"Diana Nicoleta Popa","orcid":"https://orcid.org/0000-0001-7039-3792"},"institutions":[{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Diana Nicoleta Popa","raw_affiliation_strings":["Laboratoire d\u2019Informatique de Grenoble, Universit\u00e9 Grenoble Alpes, 700 Avenue Centrale, 38401 Saint-Martin-d\u2019H\u00e8res, France","Naver Labs Europe, 6 Chemin de Maupertuis, 38240 Meylan, France","Laboratoire d\u2019Informatique de Grenoble, Universit\u00e9 Grenoble Alpes, 700 Avenue Centrale, 38401 Saint-Martin-d\u2019H\u00e8res, France; Naver Labs Europe, 6 Chemin de Maupertuis, 38240 Meylan, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire d\u2019Informatique de Grenoble, Universit\u00e9 Grenoble Alpes, 700 Avenue Centrale, 38401 Saint-Martin-d\u2019H\u00e8res, France","institution_ids":["https://openalex.org/I4210104430","https://openalex.org/I899635006"]},{"raw_affiliation_string":"Naver Labs Europe, 6 Chemin de Maupertuis, 38240 Meylan, France","institution_ids":[]},{"raw_affiliation_string":"Laboratoire d\u2019Informatique de Grenoble, Universit\u00e9 Grenoble Alpes, 700 Avenue Centrale, 38401 Saint-Martin-d\u2019H\u00e8res, France; Naver Labs Europe, 6 Chemin de Maupertuis, 38240 Meylan, France","institution_ids":["https://openalex.org/I4210104430","https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113478975","display_name":"Julien P\u00e9rez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julien Perez","raw_affiliation_strings":["Naver Labs Europe, 6 Chemin de Maupertuis, 38240 Meylan, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naver Labs Europe, 6 Chemin de Maupertuis, 38240 Meylan, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084321238","display_name":"James Henderson","orcid":"https://orcid.org/0000-0003-3714-4799"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"James Henderson","raw_affiliation_strings":["Idiap Research Institute, 19 Rue Marconi, 1920 Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, 19 Rue Marconi, 1920 Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014352159","display_name":"\u00c9ric Gaussier","orcid":"https://orcid.org/0000-0002-8858-3233"},"institutions":[{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Eric Gaussier","raw_affiliation_strings":["Laboratoire d\u2019Informatique de Grenoble, Universit\u00e9 Grenoble Alpes, 700 Avenue Centrale, 38401 Saint-Martin-d\u2019H\u00e8res, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire d\u2019Informatique de Grenoble, Universit\u00e9 Grenoble Alpes, 700 Avenue Centrale, 38401 Saint-Martin-d\u2019H\u00e8res, France","institution_ids":["https://openalex.org/I4210104430","https://openalex.org/I899635006"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081413017"],"corresponding_institution_ids":["https://openalex.org/I4210104430","https://openalex.org/I899635006"],"apc_list":{"value":3160,"currency":"USD","value_usd":3160},"apc_paid":null,"fwci":0.142,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60034243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":"27","issue":"6","first_page":"691","last_page":"720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9850999712944031,"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":0.8690048456192017},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7379099130630493},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7204700708389282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6500291228294373},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5877032279968262},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5716687440872192},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5667511224746704},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5140408277511597},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48327332735061646},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.410234272480011},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1913735568523407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8690048456192017},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7379099130630493},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7204700708389282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6500291228294373},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5877032279968262},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5716687440872192},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5667511224746704},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5140408277511597},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48327332735061646},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.410234272480011},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1913735568523407},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324920000297","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324920000297","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W97201605","https://openalex.org/W131533222","https://openalex.org/W205829674","https://openalex.org/W1484288670","https://openalex.org/W1503259811","https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W1632114991","https://openalex.org/W1832693441","https://openalex.org/W1840435438","https://openalex.org/W1889268436","https://openalex.org/W1984052055","https://openalex.org/W2005181355","https://openalex.org/W2064675550","https://openalex.org/W2070246124","https://openalex.org/W2103305545","https://openalex.org/W2114524997","https://openalex.org/W2118090838","https://openalex.org/W2120615054","https://openalex.org/W2125031621","https://openalex.org/W2127795553","https://openalex.org/W2128870637","https://openalex.org/W2133280805","https://openalex.org/W2133564696","https://openalex.org/W2143431851","https://openalex.org/W2145658888","https://openalex.org/W2147489358","https://openalex.org/W2153579005","https://openalex.org/W2158899491","https://openalex.org/W2160660844","https://openalex.org/W2162456950","https://openalex.org/W2163455955","https://openalex.org/W2163953154","https://openalex.org/W2166776180","https://openalex.org/W2250539671","https://openalex.org/W2251329024","https://openalex.org/W2251537235","https://openalex.org/W2251771443","https://openalex.org/W2251874715","https://openalex.org/W2251939518","https://openalex.org/W2254842198","https://openalex.org/W2262907013","https://openalex.org/W2415204069","https://openalex.org/W2432356473","https://openalex.org/W2507974895","https://openalex.org/W2572064709","https://openalex.org/W2613904329","https://openalex.org/W2626778328","https://openalex.org/W2740711318","https://openalex.org/W2790235966","https://openalex.org/W2896457183","https://openalex.org/W2950133940","https://openalex.org/W2950577311","https://openalex.org/W2950726992","https://openalex.org/W2950910987","https://openalex.org/W2952064673","https://openalex.org/W2955797234","https://openalex.org/W2962739339","https://openalex.org/W2962772384","https://openalex.org/W2963082277","https://openalex.org/W2963231544","https://openalex.org/W2963563735","https://openalex.org/W2963901637","https://openalex.org/W2963918774","https://openalex.org/W2964232431","https://openalex.org/W2964318298","https://openalex.org/W3104717349","https://openalex.org/W4255198209","https://openalex.org/W4285719527","https://openalex.org/W6629028937","https://openalex.org/W6631190155","https://openalex.org/W6637433842","https://openalex.org/W6679915538","https://openalex.org/W6718112784","https://openalex.org/W6732015709","https://openalex.org/W6737778391","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4287125478","https://openalex.org/W3171594500","https://openalex.org/W3170826848"],"abstract_inverted_index":{"Abstract":[0],"Distributional":[1],"semantic":[2],"word":[3,37,51,56,100,226,231,248],"representations":[4,167,232,281,286],"are":[5,123],"at":[6],"the":[7,35,69,114,162,189,208,215,230,237,276,279],"basis":[8],"of":[9,75,88,117,150,164,170,174,240,255,264,278,287],"most":[10],"modern":[11],"NLP":[12],"systems.":[13],"Their":[14],"usefulness":[15,163],"has":[16],"been":[17,234],"proven":[18],"across":[19],"various":[20,290],"tasks,":[21],"particularly":[22],"as":[23,104,168],"inputs":[24],"to":[25,39,90,107,125,156,201,269,283],"deep":[26,127,171,261],"learning":[27,128,135,172,183,262],"models.":[28],"Beyond":[29],"that,":[30],"much":[31],"work":[32,48,78],"investigated":[33,49],"fine-tuning":[34],"generic":[36],"embeddings":[38,53,145,184,200,223],"leverage":[40],"linguistic":[41,115,151],"knowledge":[42],"from":[43,82,113,193,242],"large":[44,63,86,253],"lexical":[45,64],"resources.":[46,65],"Some":[47],"context-dependent":[50],"token":[52,144,166,203,222,280],"motivated":[54],"by":[55,182,196],"sense":[57],"disambiguation,":[58],"using":[59],"sequential":[60],"context":[61,241],"and":[62,85,188,258,292],"More":[66],"recently,":[67],"acknowledging":[68],"need":[70],"for":[71,141,185,266,289],"an":[72,132,147],"in-context":[73],"representation":[74],"words,":[76],"some":[77],"leveraged":[79],"information":[80,111],"derived":[81,112],"language":[83],"modelling":[84],"amounts":[87],"data":[89],"induce":[91],"contextualised":[92],"representations.":[93,204],"In":[94],"this":[95,154],"paper,":[96],"we":[97,160],"investigate":[98,161],"Syntax-Aware":[99],"Token":[101],"Embeddings":[102],"(SATokE)":[103],"a":[105,118,126,179,252],"way":[106],"explicitly":[108],"encode":[109,178],"specific":[110],"analysis":[116],"sentence":[119,180,267,291,293],"in":[120],"vectors":[121],"which":[122],"input":[124],"model.":[129],"We":[130,177,250,273],"propose":[131],"efficient":[133],"unsupervised":[134],"algorithm":[136],"based":[137],"on":[138,236],"tensor":[139],"factorisation":[140],"computing":[142],"these":[143],"given":[146],"arbitrary":[148],"graph":[149],"structure.":[152],"Applying":[153],"method":[155],"syntactic":[157],"dependency":[158],"structures,":[159],"such":[165],"part":[169],"models":[173,265],"text":[175],"understanding.":[176],"either":[181],"its":[186],"tokens":[187],"relations":[190],"between":[191],"them":[192],"scratch":[194],"or":[195],"leveraging":[197],"pre-trained":[198,246],"relation":[199],"infer":[202],"Given":[205],"sufficient":[206],"data,":[207],"former":[209],"is":[210],"slightly":[211],"more":[212,220],"accurate":[213],"than":[214,224],"latter,":[216],"yet":[217],"both":[218],"provide":[219],"informative":[221],"standard":[225],"representations,":[227],"even":[228],"when":[229],"have":[233],"learned":[235],"same":[238],"type":[239],"larger":[243],"corpora":[244],"(namely":[245],"dependency-based":[247],"embeddings).":[249],"use":[251],"set":[254],"supervised":[256],"tasks":[257],"two":[259],"major":[260],"families":[263],"understanding":[268],"evaluate":[270],"our":[271],"proposal.":[272],"empirically":[274],"demonstrate":[275],"superiority":[277],"compared":[282],"popular":[284],"distributional":[285],"words":[288],"pair":[294],"classification":[295],"tasks.":[296]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}