{"id":"https://openalex.org/W2311143338","doi":"https://doi.org/10.1162/coli_a_00250","title":"When the Whole Is Less Than the Sum of Its Parts: How Composition Affects PMI Values in Distributional Semantic Vectors","display_name":"When the Whole Is Less Than the Sum of Its Parts: How Composition Affects PMI Values in Distributional Semantic Vectors","publication_year":2016,"publication_date":"2016-04-27","ids":{"openalex":"https://openalex.org/W2311143338","doi":"https://doi.org/10.1162/coli_a_00250","mag":"2311143338"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00250","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00250","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00250","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00250","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074570184","display_name":"Denis Paperno","orcid":"https://orcid.org/0000-0002-8889-4066"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Denis Paperno","raw_affiliation_strings":["University of Trento"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612405","display_name":"Marco Baroni","orcid":"https://orcid.org/0000-0001-5066-3580"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Baroni","raw_affiliation_strings":["University of Trento"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8581,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.9534137,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"42","issue":"2","first_page":"345","last_page":"350"},"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":0.9998999834060669,"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/T12090","display_name":"Language and cultural evolution","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pointwise-mutual-information","display_name":"Pointwise mutual information","score":0.7224026918411255},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6993833780288696},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6519588232040405},{"id":"https://openalex.org/keywords/pointwise","display_name":"Pointwise","score":0.5926159620285034},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5848744511604309},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.5466712713241577},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5193760991096497},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5005607604980469},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4996616840362549},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47331559658050537},{"id":"https://openalex.org/keywords/cohesion","display_name":"Cohesion (chemistry)","score":0.470132440328598},{"id":"https://openalex.org/keywords/distributional-semantics","display_name":"Distributional semantics","score":0.4650152325630188},{"id":"https://openalex.org/keywords/adjective","display_name":"Adjective","score":0.46045687794685364},{"id":"https://openalex.org/keywords/noun-phrase","display_name":"Noun phrase","score":0.4532613754272461},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.4139007031917572},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28048551082611084},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2647387385368347},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.2545739412307739},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.21463432908058167}],"concepts":[{"id":"https://openalex.org/C7797323","wikidata":"https://www.wikidata.org/wiki/Q3798612","display_name":"Pointwise mutual information","level":3,"score":0.7224026918411255},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6993833780288696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6519588232040405},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.5926159620285034},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5848744511604309},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.5466712713241577},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5193760991096497},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5005607604980469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4996616840362549},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47331559658050537},{"id":"https://openalex.org/C104054115","wikidata":"https://www.wikidata.org/wiki/Q216828","display_name":"Cohesion (chemistry)","level":2,"score":0.470132440328598},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.4650152325630188},{"id":"https://openalex.org/C2777683214","wikidata":"https://www.wikidata.org/wiki/Q34698","display_name":"Adjective","level":3,"score":0.46045687794685364},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.4532613754272461},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.4139007031917572},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28048551082611084},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2647387385368347},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2545739412307739},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.21463432908058167},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1162/coli_a_00250","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00250","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00250","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:repositori-api.upf.edu:10230/45934","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/45934","pdf_url":null,"source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:doaj.org/article:71bc096645cb4eaa98706f09dea49375","is_oa":false,"landing_page_url":"https://doaj.org/article/71bc096645cb4eaa98706f09dea49375","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 42, Iss 2 (2021)","raw_type":"article"},{"id":"pmh:oai:zenodo.org:49780","is_oa":true,"landing_page_url":"https://www.openaccessrepository.it/record/49780","pdf_url":null,"source":{"id":"https://openalex.org/S4306402478","display_name":"INFM-OAR (INFN Catania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210116497","host_organization_name":"Istituto Nazionale di Fisica Nucleare, Sezione di Catania","host_organization_lineage":["https://openalex.org/I4210116497"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00250","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00250","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00250","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2311143338.pdf","grobid_xml":"https://content.openalex.org/works/W2311143338.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1530392788","https://openalex.org/W1593045043","https://openalex.org/W1662133657","https://openalex.org/W1984052055","https://openalex.org/W1992009922"],"related_works":["https://openalex.org/W2925146703","https://openalex.org/W3119564760","https://openalex.org/W1570461899","https://openalex.org/W4380987972","https://openalex.org/W2251582277","https://openalex.org/W2127863960","https://openalex.org/W1587061654","https://openalex.org/W2293644338","https://openalex.org/W4280505672","https://openalex.org/W2311143338"],"abstract_inverted_index":{"Distributional":[0],"semantic":[1],"models,":[2,31],"deriving":[3],"vector-based":[4],"word":[5,10],"representations":[6,38],"from":[7,37,61],"patterns":[8],"of":[9,39,51,76,107,114,120,132,135,162],"usage":[11],"in":[12,28,83,116],"corpora,":[13],"have":[14],"many":[15],"useful":[16],"applications":[17],"(Turney":[18],"and":[19,44,80,111],"Pantel":[20],"2010":[21,46],").":[22,47],"Recently,":[23],"there":[24],"has":[25],"been":[26],"interest":[27],"compositional":[29],"distributional":[30,52],"which":[32,89],"derive":[33],"vectors":[34,53],"for":[35],"phrases":[36],"their":[40],"constituent":[41],"words":[42],"(Mitchell":[43],"Lapata":[45],"Often,":[48],"the":[49,70,73,101,104,112,117,121,133,136,140,144],"values":[50],"are":[54],"pointwise":[55],"mutual":[56],"information":[57],"(PMI)":[58],"scores":[59],"obtained":[60],"raw":[62],"co-occurrence":[63],"counts.":[64],"In":[65],"this":[66,156],"article":[67],"we":[68],"study":[69],"relation":[71],"between":[72,103],"PMI":[74,105],"dimensions":[75,119],"a":[77,108,130],"phrase":[78,109],"vector":[79,110],"its":[81],"components":[82],"order":[84],"to":[85],"gain":[86],"insights":[87],"into":[88],"operations":[90],"an":[91,125,160],"adequate":[92],"composition":[93],"model":[94],"should":[95],"perform.":[96],"We":[97,153],"show":[98],"mathematically":[99],"that":[100],"difference":[102],"dimension":[106,142],"sum":[113],"PMIs":[115],"corresponding":[118],"phrase's":[122,145],"parts":[123],"is":[124],"independently":[126],"interpretable":[127],"value,":[128],"namely,":[129],"quantification":[131],"impact":[134],"context":[137],"associated":[138],"with":[139],"relevant":[141],"on":[143],"internal":[146],"cohesion,":[147],"as":[148],"also":[149],"measured":[150],"by":[151],"PMI.":[152],"then":[154],"explore":[155],"quantity":[157],"empirically,":[158],"through":[159],"analysis":[161],"adjective\u2013noun":[163],"composition.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}