{"id":"https://openalex.org/W4395680635","doi":"https://doi.org/10.1162/tacl_a_00657","title":"Semantics of Multiword Expressions in Transformer-Based Models: A Survey","display_name":"Semantics of Multiword Expressions in Transformer-Based Models: A Survey","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4395680635","doi":"https://doi.org/10.1162/tacl_a_00657"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00657","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00657","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00657/2367417/tacl_a_00657.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for 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/tacl/article-pdf/doi/10.1162/tacl_a_00657/2367417/tacl_a_00657.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072802537","display_name":"Filip Mileti\u0107","orcid":"https://orcid.org/0000-0001-5402-5818"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Filip Mileti\u0107","raw_affiliation_strings":["Institute for Natural Language Processing, University of Stuttgart, Germany. filip.miletic@ims.uni-stuttgart.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing, University of Stuttgart, Germany. filip.miletic@ims.uni-stuttgart.de","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036567696","display_name":"Sabine Schulte im Walde","orcid":"https://orcid.org/0000-0002-8975-6255"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sabine Schulte im Walde","raw_affiliation_strings":["Institute for Natural Language Processing, University of Stuttgart, Germany. schulte@ims.uni-stuttgart.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing, University of Stuttgart, Germany. schulte@ims.uni-stuttgart.de","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5036567696","https://openalex.org/A5072802537"],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":1.3892,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83228826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"12","issue":null,"first_page":"593","last_page":"612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/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/T12031","display_name":"Speech and dialogue systems","score":0.9922000169754028,"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":0.8782217502593994},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6437928676605225},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.541902482509613},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5147514343261719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3778257966041565},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.26069319248199463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8782217502593994},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6437928676605225},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.541902482509613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5147514343261719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3778257966041565},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26069319248199463},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00657","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00657","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00657/2367417/tacl_a_00657.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8b9de948e43b408a8f4a0cd4d12c7818","is_oa":true,"landing_page_url":"https://doaj.org/article/8b9de948e43b408a8f4a0cd4d12c7818","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 12 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00657","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00657","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00657/2367417/tacl_a_00657.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395680635.pdf"},"referenced_works_count":90,"referenced_works":["https://openalex.org/W1410460","https://openalex.org/W1498763386","https://openalex.org/W1969386212","https://openalex.org/W2045705339","https://openalex.org/W2069117212","https://openalex.org/W2251882135","https://openalex.org/W2524182563","https://openalex.org/W2612690371","https://openalex.org/W2619927796","https://openalex.org/W2664496537","https://openalex.org/W2898795086","https://openalex.org/W2898914189","https://openalex.org/W2912764446","https://openalex.org/W2945901489","https://openalex.org/W2948947170","https://openalex.org/W2954604190","https://openalex.org/W2962694015","https://openalex.org/W2963341956","https://openalex.org/W2965373594","https://openalex.org/W2966176804","https://openalex.org/W2970641574","https://openalex.org/W2988217457","https://openalex.org/W2999905431","https://openalex.org/W3004346089","https://openalex.org/W3011411500","https://openalex.org/W3034999214","https://openalex.org/W3035390927","https://openalex.org/W3082470847","https://openalex.org/W3099178230","https://openalex.org/W3100475986","https://openalex.org/W3100919478","https://openalex.org/W3114208036","https://openalex.org/W3117890995","https://openalex.org/W3118485687","https://openalex.org/W3127043245","https://openalex.org/W3144320030","https://openalex.org/W3152698349","https://openalex.org/W3153626078","https://openalex.org/W3155825510","https://openalex.org/W3173508720","https://openalex.org/W3173710818","https://openalex.org/W3183582945","https://openalex.org/W3185437894","https://openalex.org/W3198711991","https://openalex.org/W3201254286","https://openalex.org/W3206846084","https://openalex.org/W3207350353","https://openalex.org/W3212187545","https://openalex.org/W4221086658","https://openalex.org/W4225090118","https://openalex.org/W4285280911","https://openalex.org/W4287854757","https://openalex.org/W4287888493","https://openalex.org/W4287891466","https://openalex.org/W4288089799","https://openalex.org/W4312558730","https://openalex.org/W4376652178","https://openalex.org/W4385570971","https://openalex.org/W4385573459","https://openalex.org/W4385573511","https://openalex.org/W4385573956","https://openalex.org/W4386566329","https://openalex.org/W4386566642","https://openalex.org/W4386566774","https://openalex.org/W4386566901","https://openalex.org/W4386566907","https://openalex.org/W4386566988","https://openalex.org/W4386576793","https://openalex.org/W4389520059","https://openalex.org/W4391156274","https://openalex.org/W6601031416","https://openalex.org/W6627994056","https://openalex.org/W6638796586","https://openalex.org/W6680585821","https://openalex.org/W6729654139","https://openalex.org/W6739901393","https://openalex.org/W6748621776","https://openalex.org/W6752544232","https://openalex.org/W6763527631","https://openalex.org/W6763701032","https://openalex.org/W6767913650","https://openalex.org/W6768021236","https://openalex.org/W6768851824","https://openalex.org/W6769627184","https://openalex.org/W6769727397","https://openalex.org/W6778507664","https://openalex.org/W6778777187","https://openalex.org/W6778883912","https://openalex.org/W6779068807","https://openalex.org/W6927495154"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W4395014643","https://openalex.org/W4391913857","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Abstract":[0],"Multiword":[1],"expressions":[2],"(MWEs)":[3],"are":[4,19],"composed":[5],"of":[6,13,45,80,96,105],"multiple":[7],"words":[8],"and":[9,24,67,94],"exhibit":[10],"variable":[11],"degrees":[12],"compositionality.":[14],"As":[15],"such,":[16],"their":[17],"meanings":[18],"notoriously":[20],"difficult":[21],"to":[22,28,108],"model,":[23],"it":[25],"is":[26,72],"unclear":[27],"what":[29],"extent":[30],"this":[31,37],"issue":[32],"affects":[33],"transformer":[34,49,106],"architectures.":[35],"Addressing":[36],"gap,":[38],"we":[39,114],"provide":[40],"the":[41,81,103,116],"first":[42],"in-depth":[43],"survey":[44],"MWE":[46,57,70],"processing":[47],"with":[48],"models.":[50],"We":[51],"overall":[52,101],"find":[53],"that":[54],"they":[55],"capture":[56,110],"semantics":[58],"inconsistently,":[59],"as":[60,90],"shown":[61],"by":[62],"reliance":[63],"on":[64],"surface":[65],"patterns":[66],"memorized":[68],"information.":[69],"meaning":[71],"also":[73],"strongly":[74],"localized,":[75],"predominantly":[76],"in":[77],"early":[78],"layers":[79],"architecture.":[82],"Representations":[83],"benefit":[84],"from":[85],"specific":[86],"linguistic":[87],"properties,":[88],"such":[89],"lower":[91],"semantic":[92],"idiosyncrasy":[93],"ambiguity":[95],"target":[97],"expressions.":[98],"Our":[99],"findings":[100],"question":[102],"ability":[104],"models":[107],"robustly":[109],"fine-grained":[111],"semantics.":[112],"Furthermore,":[113],"highlight":[115],"need":[117],"for":[118],"more":[119],"directly":[120],"comparable":[121],"evaluation":[122],"setups.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
