{"id":"https://openalex.org/W2176363684","doi":"https://doi.org/10.3115/v1/w15-0904","title":"A Multiword Expression Data Set: Annotating Non-Compositionality and Conventionalization for English Noun Compounds","display_name":"A Multiword Expression Data Set: Annotating Non-Compositionality and Conventionalization for English Noun Compounds","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2176363684","doi":"https://doi.org/10.3115/v1/w15-0904","mag":"2176363684"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w15-0904","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w15-0904","pdf_url":"https://www.aclweb.org/anthology/W15-0904.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 11th Workshop on Multiword Expressions","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-0904.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060826374","display_name":"Meghdad Farahmand","orcid":null},"institutions":[{"id":"https://openalex.org/I114457229","display_name":"University of Geneva","ror":"https://ror.org/01swzsf04","country_code":"CH","type":"education","lineage":["https://openalex.org/I114457229"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Meghdad Farahmand","raw_affiliation_strings":["University of Geneva Geneva, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Geneva Geneva, Switzerland","institution_ids":["https://openalex.org/I114457229"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Aaron Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Aaron Smith","raw_affiliation_strings":["Uppsala University Uppsala, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uppsala University Uppsala, Sweden","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077063699","display_name":"Joakim Nivre","orcid":null},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Joakim Nivre","raw_affiliation_strings":["Uppsala University Uppsala, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uppsala University Uppsala, Sweden","institution_ids":["https://openalex.org/I123387679"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5268,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.95886848,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"33"},"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":0.9988999962806702,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8305100798606873},{"id":"https://openalex.org/keywords/principle-of-compositionality","display_name":"Principle of compositionality","score":0.7820915579795837},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7076667547225952},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.657765805721283},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5918211340904236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5900753736495972},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.46506741642951965},{"id":"https://openalex.org/keywords/noun-phrase","display_name":"Noun phrase","score":0.46074405312538147},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.43542343378067017},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.133225679397583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8305100798606873},{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.7820915579795837},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7076667547225952},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.657765805721283},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5918211340904236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5900753736495972},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.46506741642951965},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.46074405312538147},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.43542343378067017},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.133225679397583}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/v1/w15-0904","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w15-0904","pdf_url":"https://www.aclweb.org/anthology/W15-0904.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 11th Workshop on Multiword Expressions","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/v1/w15-0904","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w15-0904","pdf_url":"https://www.aclweb.org/anthology/W15-0904.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 11th Workshop on Multiword Expressions","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2176363684.pdf","grobid_xml":"https://content.openalex.org/works/W2176363684.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W25517462","https://openalex.org/W170166889","https://openalex.org/W638675188","https://openalex.org/W1498763386","https://openalex.org/W1574901103","https://openalex.org/W1847856012","https://openalex.org/W1940278502","https://openalex.org/W2091477393","https://openalex.org/W2147955622","https://openalex.org/W2164777277"],"related_works":["https://openalex.org/W4251923961","https://openalex.org/W1526190050","https://openalex.org/W2477397717","https://openalex.org/W2500457737","https://openalex.org/W2010490241","https://openalex.org/W4287025733","https://openalex.org/W4317425742","https://openalex.org/W3192500523","https://openalex.org/W4241382148","https://openalex.org/W2025590371"],"abstract_inverted_index":{"Scarcity":[0],"of":[1,32,54,82,91,95,100,102],"multiword":[2,33],"expression":[3],"data":[4,39,69],"sets":[5],"raises":[6],"a":[7,30,37,52],"fundamental":[8],"challenge":[9],"to":[10,25,79],"evaluating":[11],"the":[12,83,96],"systems":[13],"that":[14],"deal":[15],"with":[16],"these":[17],"linguistic":[18],"structures.":[19],"In":[20],"this":[21,27,68],"work":[22,76],"we":[23],"attempt":[24],"address":[26,80],"problem":[28],"for":[29],"subclass":[31],"expressions":[34],"by":[35,42,46],"producing":[36],"large":[38],"set":[40,53,70],"annotated":[41,58,92],"experts":[43],"and":[44,63,98],"validated":[45],"common":[47,72],"statistical":[48],"measures.":[49],"We":[50,66],"present":[51],"1048":[55],"noun-noun":[56],"compounds":[57],"as":[59,88],"non-compositional,":[60],"compositional,":[61],"conventionalized":[62],"not":[64],"conventionalized.":[65],"build":[67],"following":[71],"trends":[73],"in":[74],"previous":[75],"while":[77],"trying":[78],"some":[81],"well":[84],"known":[85],"issues":[86],"such":[87],"small":[89],"number":[90],"instances,":[93],"quality":[94],"annotations,":[97],"lack":[99],"availability":[101],"true":[103],"negative":[104],"instances.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
