{"id":"https://openalex.org/W2767696689","doi":"https://doi.org/10.1145/3132847.3132984","title":"A Matrix-Vector Recurrent Unit Model for Capturing Compositional Semantics in Phrase Embeddings","display_name":"A Matrix-Vector Recurrent Unit Model for Capturing Compositional Semantics in Phrase Embeddings","publication_year":2017,"publication_date":"2017-11-06","ids":{"openalex":"https://openalex.org/W2767696689","doi":"https://doi.org/10.1145/3132847.3132984","mag":"2767696689"},"language":"en","primary_location":{"id":"doi:10.1145/3132847.3132984","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132847.3132984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100431149","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0001-8007-2503"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["University of Western Australia, Perth, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641142","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-7409-0948"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["University of Western Australia, Perth, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009328394","display_name":"Chris McDonald","orcid":"https://orcid.org/0000-0003-4667-541X"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chris McDonald","raw_affiliation_strings":["University of Western Australia, Perth, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177877127"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1499","last_page":"1507"},"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":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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9993000030517578,"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":0.8266268968582153},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7763824462890625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7753947973251343},{"id":"https://openalex.org/keywords/principle-of-compositionality","display_name":"Principle of compositionality","score":0.7475585341453552},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6150557994842529},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5438535809516907},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5259162187576294},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5100238919258118},{"id":"https://openalex.org/keywords/distributional-semantics","display_name":"Distributional semantics","score":0.458933562040329},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.3064601719379425},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10245481133460999}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8266268968582153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7763824462890625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7753947973251343},{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.7475585341453552},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6150557994842529},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5438535809516907},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5259162187576294},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5100238919258118},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.458933562040329},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3064601719379425},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10245481133460999},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3132847.3132984","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132847.3132984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/3a4efef6-e31c-4c53-9271-8d2e473cbff1","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/3a4efef6-e31c-4c53-9271-8d2e473cbff1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402492","display_name":"UWA Profiles and Research Repository (UWA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wang , R , Liu , W & McDonald , C 2017 , A matrix-vector recurrent unit model for capturing compositional semantics in phrase embeddings . in CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management . vol. Part F131841 , Association for Computing Machinery (ACM) , pp. 1499-1507 , 26th ACM International Conference on Information and Knowledge Management, CIKM 2017 , Singapore , Singapore , 6/11/17 . https://doi.org/10.1145/3132847.3132984","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6000000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W42251416","https://openalex.org/W71795751","https://openalex.org/W179875071","https://openalex.org/W1526096287","https://openalex.org/W1608322251","https://openalex.org/W1832693441","https://openalex.org/W1889268436","https://openalex.org/W1924770834","https://openalex.org/W1973942085","https://openalex.org/W1984052055","https://openalex.org/W2049107599","https://openalex.org/W2054045793","https://openalex.org/W2064675550","https://openalex.org/W2068956026","https://openalex.org/W2100693535","https://openalex.org/W2103305545","https://openalex.org/W2110485445","https://openalex.org/W2120615054","https://openalex.org/W2130942839","https://openalex.org/W2131744502","https://openalex.org/W2137607259","https://openalex.org/W2151835172","https://openalex.org/W2153579005","https://openalex.org/W2157331557","https://openalex.org/W2160745555","https://openalex.org/W2250644439","https://openalex.org/W2250966211","https://openalex.org/W2251471769","https://openalex.org/W2265846598","https://openalex.org/W2399456070","https://openalex.org/W2400801499","https://openalex.org/W2950726992","https://openalex.org/W2952064673","https://openalex.org/W2953061907","https://openalex.org/W2998704965","https://openalex.org/W3034155521","https://openalex.org/W3099386342","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2795843251","https://openalex.org/W1715304901","https://openalex.org/W2912764446","https://openalex.org/W2158324326","https://openalex.org/W2784926331","https://openalex.org/W84019336","https://openalex.org/W2515845560","https://openalex.org/W2170770969","https://openalex.org/W1847856012","https://openalex.org/W2572858686"],"abstract_inverted_index":{"The":[0,110,135],"meaning":[1,11],"of":[2,12,20,56,85,104,120],"a":[3,89,108,113],"multi-word":[4],"phrase":[5,148],"not":[6],"only":[7],"depends":[8],"on":[9,140,182],"the":[10,18,25,47,51,54,57,62,73,83,97,101,118,168],"its":[13],"constituent":[14],"words,":[15],"but":[16],"also":[17],"rules":[19],"composing":[21],"them":[22],"to":[23,70,116],"give":[24],"so-called":[26],"compositional":[27,36,74,102],"semantic.":[28],"However,":[29],"many":[30],"deep":[31,172],"learning":[32,35,173],"models":[33,66],"for":[34,61,122],"semantics":[37,84],"target":[38],"specific":[39,157],"NLP":[40,145],"tasks":[41,146],"such":[42,131],"as":[43,132],"sentiment":[44,152],"classification.":[45],"Consequently,":[46],"word":[48,106],"embeddings":[49],"encode":[50,72],"lexical":[52],"semantics,":[53],"weights":[55],"networks":[58],"are":[59,79],"optimised":[60],"classification":[63],"task.":[64],"Such":[65],"have":[67],"no":[68],"mechanisms":[69],"explicitly":[71],"rules,":[75],"and":[76,143,155,170,178],"hence":[77],"they":[78],"insufficient":[80],"in":[81],"capturing":[82],"phrases.":[86],"We":[87,161],"present":[88],"novel":[90],"recurrent":[91,114],"computational":[92],"mechanism":[93],"that":[94,163],"specifically":[95],"learns":[96],"compositionality":[98],"by":[99],"encoding":[100],"rule":[103],"each":[105],"into":[107],"matrix.":[109],"network":[111],"uses":[112],"architecture":[115],"capture":[117],"order":[119],"words":[121],"phrases":[123],"with":[124],"various":[125],"lengths":[126],"without":[127],"requiring":[128],"extra":[129],"preprocessing":[130],"part-of-speech":[133],"tagging.":[134],"model":[136,165],"is":[137],"thoroughly":[138],"evaluated":[139],"both":[141],"supervised":[142],"unsupervised":[144],"including":[147],"similarity,":[149],"noun-modifier":[150],"questions,":[151],"distribution":[153],"prediction,":[154],"domain":[156],"term":[158],"identification":[159],"tasks.":[160],"demonstrate":[162],"our":[164],"consistently":[166],"outperforms":[167],"LSTM":[169],"CNN":[171],"models,":[174],"simple":[175],"algebraic":[176],"compositions,":[177],"other":[179],"popular":[180],"baselines":[181],"different":[183],"datasets.":[184]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}