{"id":"https://openalex.org/W3183582945","doi":"https://doi.org/10.18653/v1/2021.mwe-1.7","title":"Finding BERT\u2019s Idiomatic Key","display_name":"Finding BERT\u2019s Idiomatic Key","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3183582945","doi":"https://doi.org/10.18653/v1/2021.mwe-1.7","mag":"3183582945"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.mwe-1.7","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.mwe-1.7","pdf_url":"https://aclanthology.org/2021.mwe-1.7.pdf","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 17th Workshop on Multiword Expressions (MWE 2021)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2021.mwe-1.7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021204772","display_name":"Vasudevan Nedumpozhimana","orcid":"https://orcid.org/0000-0001-5161-8925"},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Vasudevan Nedumpozhimana","raw_affiliation_strings":["ADAPT Research Center","Technological University Dublin Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ADAPT Research Center","institution_ids":[]},{"raw_affiliation_string":"Technological University Dublin Dublin, Ireland","institution_ids":["https://openalex.org/I4210144925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079991004","display_name":"John D. Kelleher","orcid":"https://orcid.org/0000-0001-6462-3248"},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"John Kelleher","raw_affiliation_strings":["ADAPT Research Center","Technological University Dublin Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ADAPT Research Center","institution_ids":[]},{"raw_affiliation_string":"Technological University Dublin Dublin, Ireland","institution_ids":["https://openalex.org/I4210144925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210144925"],"apc_list":null,"apc_paid":null,"fwci":2.4888,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91499141,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T13629","display_name":"Text Readability and Simplification","score":0.9980000257492065,"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/sentence","display_name":"Sentence","score":0.8336593508720398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7418426275253296},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6806690692901611},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6614484786987305},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6385934352874756},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6227914094924927},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.6077193021774292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5361988544464111},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5268962383270264},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4206105172634125},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.1439042091369629},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.10623514652252197},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07084348797798157},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.05540230870246887}],"concepts":[{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.8336593508720398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7418426275253296},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6806690692901611},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6614484786987305},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6385934352874756},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6227914094924927},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.6077193021774292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5361988544464111},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5268962383270264},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4206105172634125},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.1439042091369629},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.10623514652252197},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07084348797798157},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.05540230870246887},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2021.mwe-1.7","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.mwe-1.7","pdf_url":"https://aclanthology.org/2021.mwe-1.7.pdf","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 17th Workshop on Multiword Expressions (MWE 2021)","raw_type":"proceedings-article"},{"id":"pmh:oai:arrow.tudublin.ie:scschcomcon-1337","is_oa":true,"landing_page_url":"https://arrow.tudublin.ie/scschcomcon/316","pdf_url":null,"source":{"id":"https://openalex.org/S4377196307","display_name":"Arrow - TU Dublin (Technological University Dublin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210144925","host_organization_name":"Technological University Dublin","host_organization_lineage":["https://openalex.org/I4210144925"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Conference papers","raw_type":"conferencepaper"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.mwe-1.7","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.mwe-1.7","pdf_url":"https://aclanthology.org/2021.mwe-1.7.pdf","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 17th Workshop on Multiword Expressions (MWE 2021)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[{"id":"https://openalex.org/G228147372","display_name":null,"funder_award_id":"Grant 13/RC/2106","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G3993907298","display_name":"ADAPT: Centre for Digital Content Platform Research","funder_award_id":"13/RC/2106","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G6334448832","display_name":"ADAPT_Phase 2","funder_award_id":"13/RC/2106_P2","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3183582945.pdf","grobid_xml":"https://content.openalex.org/works/W3183582945.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W110339475","https://openalex.org/W1522301498","https://openalex.org/W1972686387","https://openalex.org/W1983359679","https://openalex.org/W2079547420","https://openalex.org/W2101234009","https://openalex.org/W2116394855","https://openalex.org/W2119152510","https://openalex.org/W2123215530","https://openalex.org/W2517996181","https://openalex.org/W2594108681","https://openalex.org/W2767955141","https://openalex.org/W2963341956","https://openalex.org/W2964121744","https://openalex.org/W2964204621"],"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/W1974414866","https://openalex.org/W2057568687","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W1544691147"],"abstract_inverted_index":{"Sentence":[0],"embeddings":[1],"encode":[2],"information":[3,36,63],"relating":[4],"to":[5,28],"the":[6,65,73,83],"usage":[7],"of":[8,18],"idioms":[9],"in":[10,31,75],"a":[11,16,22,32,76],"sentence.":[12],"This":[13],"paper":[14],"reports":[15],"set":[17],"experiments":[19],"that":[20,48],"combine":[21],"probing":[23],"methodology":[24],"with":[25],"input":[26],"masking":[27],"analyse":[29],"where":[30],"sentence":[33,77],"this":[34],"idiomatic":[35,50,57,87],"is":[37,52],"taken":[38],"from,":[39],"and":[40,82],"what":[41],"form":[42],"it":[43],"takes.":[44],"Our":[45],"results":[46],"indicate":[47],"BERT's":[49],"key":[51],"primarily":[53],"found":[54],"within":[55],"an":[56],"expression,":[58],"but":[59],"also":[60],"draws":[61],"on":[62],"from":[64],"surrounding":[66],"context.":[67],"Also,":[68],"BERT":[69],"can":[70],"distinguish":[71],"between":[72],"disruption":[74],"caused":[78,85],"by":[79,86],"words":[80],"missing":[81],"incongruity":[84],"usage.":[88]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9}],"updated_date":"2026-08-14T07:06:38.338062","created_date":"2025-10-10T00:00:00"}
