{"id":"https://openalex.org/W2903988268","doi":"https://doi.org/10.1609/aaai.v33i01.33017031","title":"Fast PMI-Based Word Embedding with Efficient Use of Unobserved Patterns","display_name":"Fast PMI-Based Word Embedding with Efficient Use of Unobserved Patterns","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2903988268","doi":"https://doi.org/10.1609/aaai.v33i01.33017031","mag":"2903988268"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33017031","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33017031","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v33i01.33017031","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065059896","display_name":"Behrouz Haji Soleimani","orcid":null},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Behrouz Haji Soleimani","raw_affiliation_strings":["Dalhousie University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalhousie University","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042893723","display_name":"Stan Matwin","orcid":"https://orcid.org/0000-0001-6629-8434"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Stan Matwin","raw_affiliation_strings":["Dalhousie University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalhousie University","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I129902397"],"apc_list":null,"apc_paid":null,"fwci":0.2187,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.48251983,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"33","issue":"01","first_page":"7031","last_page":"7038"},"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":0.9994999766349792,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9986000061035156,"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/pointwise-mutual-information","display_name":"Pointwise mutual information","score":0.7886861562728882},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7592912912368774},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7112738490104675},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.6585088968276978},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5725057125091553},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5596952438354492},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5373877882957458},{"id":"https://openalex.org/keywords/pointwise","display_name":"Pointwise","score":0.5329476594924927},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5139579176902771},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5070996284484863},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.48397278785705566},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.427923321723938},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.4189283549785614},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4118977189064026},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.23842307925224304},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23336219787597656},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20243504643440247},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08396881818771362}],"concepts":[{"id":"https://openalex.org/C7797323","wikidata":"https://www.wikidata.org/wiki/Q3798612","display_name":"Pointwise mutual information","level":3,"score":0.7886861562728882},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7592912912368774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7112738490104675},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.6585088968276978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5725057125091553},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5596952438354492},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5373877882957458},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.5329476594924927},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5139579176902771},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5070996284484863},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.48397278785705566},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.427923321723938},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.4189283549785614},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4118977189064026},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.23842307925224304},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23336219787597656},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20243504643440247},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08396881818771362},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33017031","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33017031","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4683","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4683","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4683/4561","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33017031","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33017031","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1593045043","https://openalex.org/W1614298861","https://openalex.org/W1662133657","https://openalex.org/W1978400666","https://openalex.org/W1998623809","https://openalex.org/W2086504823","https://openalex.org/W2097921974","https://openalex.org/W2110096996","https://openalex.org/W2125031621","https://openalex.org/W2128870637","https://openalex.org/W2147152072","https://openalex.org/W2153579005","https://openalex.org/W2250539671","https://openalex.org/W2251771443","https://openalex.org/W2260245103","https://openalex.org/W2493916176","https://openalex.org/W2518186251","https://openalex.org/W2576410866","https://openalex.org/W2585254147","https://openalex.org/W2769063188","https://openalex.org/W2788918109","https://openalex.org/W2795588493","https://openalex.org/W2888329843","https://openalex.org/W2951319051","https://openalex.org/W2963626623","https://openalex.org/W2964027067","https://openalex.org/W4206165639","https://openalex.org/W4233906699","https://openalex.org/W4252017042","https://openalex.org/W4294170691","https://openalex.org/W4307613132","https://openalex.org/W6604112372","https://openalex.org/W6624822662","https://openalex.org/W6663101273","https://openalex.org/W6681698864","https://openalex.org/W6691431627","https://openalex.org/W6691649953","https://openalex.org/W6719819555","https://openalex.org/W6748851112","https://openalex.org/W6991489767"],"related_works":["https://openalex.org/W3152143533","https://openalex.org/W3016822073","https://openalex.org/W2156553253","https://openalex.org/W2966570129","https://openalex.org/W4225872300","https://openalex.org/W3099449837","https://openalex.org/W3180389570","https://openalex.org/W3038434506","https://openalex.org/W2626769217","https://openalex.org/W2774861092"],"abstract_inverted_index":{"Continuous":[0],"word":[1,23,45,177,198],"representations":[2],"that":[3,48,82,127,190],"can":[4,128],"capture":[5],"the":[6,10,13,63,84,90,108,113,124,131,153,157,166,171,194],"semantic":[7],"information":[8],"in":[9,96,112,133,170,196],"corpus":[11],"are":[12,25],"building":[14],"blocks":[15],"of":[16,68,87,110,156,168,182],"many":[17],"natural":[18],"language":[19],"processing":[20],"tasks.":[21],"Pre-trained":[22],"embeddings":[24],"being":[26],"used":[27],"for":[28,123],"sentiment":[29],"analysis,":[30],"text":[31],"classification,":[32],"question":[33],"answering":[34],"and":[35,78,151,188],"so":[36],"on.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41,137],"propose":[42,74,118,138],"a":[43,51,119,146,202],"new":[44],"embedding":[46,178],"algorithm":[47,144,158],"works":[49],"on":[50,180],"smoothed":[52],"Positive":[53],"Pointwise":[54],"Mutual":[55],"Information":[56],"(PPMI)":[57],"matrix":[58],"which":[59,106],"is":[60,72],"obtained":[61],"from":[62,103],"word-word":[64],"co-occurrence":[65],"counts.":[66],"One":[67],"our":[69,143,191],"major":[70],"contributions":[71],"to":[73,98,142,159,165],"an":[75,79,139],"objective":[76],"function":[77],"optimization":[80],"framework":[81],"exploits":[83],"full":[85],"capacity":[86],"\u201cnegative":[88],"examples\u201d,":[89],"unobserved":[91],"or":[92],"insignificant":[93],"wordword":[94],"co-occurrences,":[95],"order":[97],"push":[99],"unrelated":[100],"words":[101,111,169],"away":[102],"each":[104],"other":[105],"improves":[107],"distribution":[109],"latent":[114,125],"space.":[115],"We":[116,173],"also":[117],"kernel":[120],"similarity":[121,199],"measure":[122],"space":[126],"effectively":[129],"calculate":[130],"similarities":[132],"high":[134],"dimensions.":[135],"Moreover,":[136],"approximate":[140],"alternative":[141],"using":[145],"modified":[147],"Vantage":[148],"Point":[149],"tree":[150],"reduce":[152],"computational":[154],"complexity":[155],"|V":[160],"|log|V":[161],"|":[162],"with":[163,184],"respect":[164],"number":[167],"vocabulary.":[172],"have":[174],"trained":[175],"various":[176],"algorithms":[179],"articles":[181],"Wikipedia":[183],"2.1":[185],"billion":[186],"tokens":[187],"show":[189],"method":[192],"outperforms":[193],"state-of-the-art":[195],"most":[197],"tasks":[200],"by":[201],"good":[203],"margin.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}