{"id":"https://openalex.org/W2508425840","doi":"https://doi.org/10.18653/v1/p16-1187","title":"Predicting the Compositionality of Nominal Compounds: Giving Word Embeddings a Hard Time","display_name":"Predicting the Compositionality of Nominal Compounds: Giving Word Embeddings a Hard Time","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2508425840","doi":"https://doi.org/10.18653/v1/p16-1187","mag":"2508425840"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p16-1187","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1187","pdf_url":"https://doi.org/10.18653/v1/p16-1187","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/p16-1187","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081307094","display_name":"Silvio Cordeiro","orcid":"https://orcid.org/0000-0002-1262-369X"},"institutions":[{"id":"https://openalex.org/I4210115196","display_name":"Laboratoire d\u2019Informatique Fondamentale de Marseille","ror":"https://ror.org/022my8t07","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I21491767","https://openalex.org/I4210115196","https://openalex.org/I4210142724","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Silvio Cordeiro","raw_affiliation_strings":["LIF - Laboratoire d'informatique Fondamentale de Marseille (Parc Scientifique et Technologique de Luminy 163, avenue de Luminy F-13288 Marseille Cedex 9 - France)"],"affiliations":[{"raw_affiliation_string":"LIF - Laboratoire d'informatique Fondamentale de Marseille (Parc Scientifique et Technologique de Luminy 163, avenue de Luminy F-13288 Marseille Cedex 9 - France)","institution_ids":["https://openalex.org/I4210115196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024831674","display_name":"Carlos Ramisch","orcid":"https://orcid.org/0000-0001-7466-9039"},"institutions":[{"id":"https://openalex.org/I4210115196","display_name":"Laboratoire d\u2019Informatique Fondamentale de Marseille","ror":"https://ror.org/022my8t07","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I21491767","https://openalex.org/I4210115196","https://openalex.org/I4210142724","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Carlos Ramisch","raw_affiliation_strings":["LIF - Laboratoire d'informatique Fondamentale de Marseille (Parc Scientifique et Technologique de Luminy 163, avenue de Luminy F-13288 Marseille Cedex 9 - France)"],"affiliations":[{"raw_affiliation_string":"LIF - Laboratoire d'informatique Fondamentale de Marseille (Parc Scientifique et Technologique de Luminy 163, avenue de Luminy F-13288 Marseille Cedex 9 - France)","institution_ids":["https://openalex.org/I4210115196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002848015","display_name":"Marco Idiart","orcid":"https://orcid.org/0000-0002-7129-3520"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Idiart","raw_affiliation_strings":["Instituto de Fisica (Av. Bento Goncalves 9500 91501-970 Porto Alegre, RS - Brazil)"],"affiliations":[{"raw_affiliation_string":"Instituto de Fisica (Av. Bento Goncalves 9500 91501-970 Porto Alegre, RS - Brazil)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053823442","display_name":"Aline Villavicencio","orcid":"https://orcid.org/0000-0002-3731-9168"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aline Villavicencio","raw_affiliation_strings":["Informatics Institute = Instituto de Inform\u00e1tica [Porto Alegre] (Caixa Postal 15064, 91.501-970 Porto Alegre - Brazil)"],"affiliations":[{"raw_affiliation_string":"Informatics Institute = Instituto de Inform\u00e1tica [Porto Alegre] (Caixa Postal 15064, 91.501-970 Porto Alegre - Brazil)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081307094"],"corresponding_institution_ids":["https://openalex.org/I4210115196"],"apc_list":null,"apc_paid":null,"fwci":11.0433,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.98331585,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1986","last_page":"1997"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T13629","display_name":"Text Readability and Simplification","score":0.9943000078201294,"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/principle-of-compositionality","display_name":"Principle of compositionality","score":0.8606163263320923},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8293097019195557},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.8099801540374756},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7188565731048584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6474770307540894},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5784714221954346},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5708701610565186},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5606052875518799},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5404276847839355},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.46470633149147034},{"id":"https://openalex.org/keywords/distributional-semantics","display_name":"Distributional semantics","score":0.45627397298812866},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.452716201543808},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4432419538497925},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10446926951408386},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09082263708114624}],"concepts":[{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.8606163263320923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8293097019195557},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.8099801540374756},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7188565731048584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6474770307540894},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5784714221954346},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5708701610565186},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5606052875518799},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5404276847839355},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.46470633149147034},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.45627397298812866},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.452716201543808},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4432419538497925},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10446926951408386},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09082263708114624},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/p16-1187","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1187","pdf_url":"https://doi.org/10.18653/v1/p16-1187","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01459914v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01459914","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2016, Berlin, Germany. pp.1986--1997, ⟨10.18653/v1/P16-1187⟩","raw_type":"Conference papers"},{"id":"pmh:oai:eprints.whiterose.ac.uk:153562","is_oa":false,"landing_page_url":"http://eprints.whiterose.ac.uk/153562/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"}],"best_oa_location":{"id":"doi:10.18653/v1/p16-1187","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1187","pdf_url":"https://doi.org/10.18653/v1/p16-1187","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2508425840.pdf","grobid_xml":"https://content.openalex.org/works/W2508425840.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W25517462","https://openalex.org/W1255655817","https://openalex.org/W1498763386","https://openalex.org/W1615991656","https://openalex.org/W1629759369","https://openalex.org/W1763741018","https://openalex.org/W1862888253","https://openalex.org/W1984052055","https://openalex.org/W2005181355","https://openalex.org/W2032498066","https://openalex.org/W2043814069","https://openalex.org/W2091477393","https://openalex.org/W2101599007","https://openalex.org/W2104066867","https://openalex.org/W2114183915","https://openalex.org/W2115736534","https://openalex.org/W2121545956","https://openalex.org/W2126168798","https://openalex.org/W2128870637","https://openalex.org/W2131744502","https://openalex.org/W2137607259","https://openalex.org/W2141365610","https://openalex.org/W2141599568","https://openalex.org/W2143017787","https://openalex.org/W2153579005","https://openalex.org/W2155870214","https://openalex.org/W2167145077","https://openalex.org/W2170682101","https://openalex.org/W2176363684","https://openalex.org/W2250213987","https://openalex.org/W2250380068","https://openalex.org/W2250539671","https://openalex.org/W2250719308","https://openalex.org/W2250977525","https://openalex.org/W2251195978","https://openalex.org/W2251687199","https://openalex.org/W2251803266","https://openalex.org/W2252262038","https://openalex.org/W2290054636","https://openalex.org/W2293834552","https://openalex.org/W2415973339","https://openalex.org/W2439228446","https://openalex.org/W2507675402","https://openalex.org/W2989939775","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2294271284","https://openalex.org/W3107848922","https://openalex.org/W1715304901","https://openalex.org/W2556436093","https://openalex.org/W2912764446","https://openalex.org/W2784926331","https://openalex.org/W84019336","https://openalex.org/W2515845560","https://openalex.org/W2931757464","https://openalex.org/W2170770969"],"abstract_inverted_index":{"Distributional":[0],"semantic":[1,31],"models":[2],"(DSMs)":[3],"are":[4],"often":[5],"evaluated":[6],"on":[7,36],"artificial":[8],"similarity":[9],"datasets":[10,38,107],"containing":[11],"single":[12],"words":[13],"or":[14,98],"fully":[15],"compositional":[16],"phrases.":[17],"We":[18,43],"present":[19],"a":[20,45,89],"large-scale":[21],"multilingual":[22],"evaluation":[23],"of":[24,30,33,47,69,75,83,102],"DSMs":[25,49],"for":[26,39,105,110],"predicting":[27],"the":[28,63,67,100,103,111],"degree":[29],"compositionality":[32],"nominal":[34],"compounds":[35],"4":[37],"English":[40],"and":[41,50,57,81],"French.":[42],"build":[44],"total":[46],"816":[48],"perform":[51],"2,856":[52],"evaluations":[53],"using":[54],"word2vec,":[55],"GloVe,":[56],"PPMI-based":[58],"models.":[59],"In":[60],"addition":[61],"to":[62,97],"DSMs,":[64],"we":[65],"compare":[66],"impact":[68],"different":[70],"parameters,":[71],"such":[72],"as":[73],"level":[74],"corpus":[76],"preprocessing,":[77],"context":[78],"window":[79],"size":[80],"number":[82],"dimensions.":[84],"The":[85],"results":[86],"obtained":[87],"have":[88],"high":[90],"correlation":[91],"with":[92],"human":[93],"judgments,":[94],"being":[95],"comparable":[96],"outperforming":[99],"state":[101],"art":[104],"some":[106],"(Spearman's":[108],"\u03c1=.82":[109],"Reddy":[112],"dataset).":[113]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}