{"id":"https://openalex.org/W2736525247","doi":"https://doi.org/10.18653/v1/d17-1198","title":"A Simple Language Model based on PMI Matrix Approximations","display_name":"A Simple Language Model based on PMI Matrix Approximations","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2736525247","doi":"https://doi.org/10.18653/v1/d17-1198","mag":"2736525247"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d17-1198","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1198","pdf_url":"https://www.aclweb.org/anthology/D17-1198.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D17-1198.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089409089","display_name":"Oren Melamud","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oren Melamud","raw_affiliation_strings":["IBM Research Yorktown Heights, NY, USA","IBM (United States), Armonk, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Yorktown Heights, NY, USA","institution_ids":[]},{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033006575","display_name":"Ido Dagan","orcid":"https://orcid.org/0000-0003-3415-3374"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ido Dagan","raw_affiliation_strings":["Computer Science Dept. Bar-Ilan University, Israel","Bar-Ilan University, Ramat Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept. Bar-Ilan University, Israel","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"Bar-Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005409420","display_name":"Jacob Goldberger","orcid":"https://orcid.org/0000-0002-2225-1914"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jacob Goldberger","raw_affiliation_strings":["Faculty of Engineering Bar-Ilan University, Israel","Bar-Ilan University, Ramat Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering Bar-Ilan University, Israel","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"Bar-Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1860","last_page":"1865"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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/word2vec","display_name":"Word2vec","score":0.8811731338500977},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6773245930671692},{"id":"https://openalex.org/keywords/pointwise-mutual-information","display_name":"Pointwise mutual information","score":0.6711164116859436},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6667377948760986},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.574347198009491},{"id":"https://openalex.org/keywords/pointwise","display_name":"Pointwise","score":0.5720776319503784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5201737880706787},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5166033506393433},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5138378739356995},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4413997530937195},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3438222408294678},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21845990419387817},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.1405787169933319}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.8811731338500977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6773245930671692},{"id":"https://openalex.org/C7797323","wikidata":"https://www.wikidata.org/wiki/Q3798612","display_name":"Pointwise mutual information","level":3,"score":0.6711164116859436},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6667377948760986},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.574347198009491},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.5720776319503784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5201737880706787},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5166033506393433},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5138378739356995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4413997530937195},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3438222408294678},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21845990419387817},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.1405787169933319},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d17-1198","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1198","pdf_url":"https://www.aclweb.org/anthology/D17-1198.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1707.05266","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.05266","pdf_url":"https://arxiv.org/pdf/1707.05266","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2736525247","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1707.05266.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1707.05266","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1707.05266","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/d17-1198","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1198","pdf_url":"https://www.aclweb.org/anthology/D17-1198.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320326823","display_name":"Intel Collaboration Research Institute for Computational Intelligence","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2736525247.pdf","grobid_xml":"https://content.openalex.org/works/W2736525247.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W932413789","https://openalex.org/W1522301498","https://openalex.org/W1591801644","https://openalex.org/W1768488313","https://openalex.org/W1917432393","https://openalex.org/W2131462252","https://openalex.org/W2259472270","https://openalex.org/W2463033603","https://openalex.org/W2951714314","https://openalex.org/W2962784628","https://openalex.org/W2962819663","https://openalex.org/W2963932686"],"related_works":["https://openalex.org/W2962828982","https://openalex.org/W2903988268","https://openalex.org/W2891378076","https://openalex.org/W2040711288","https://openalex.org/W3137558331","https://openalex.org/W162718249","https://openalex.org/W3152665294","https://openalex.org/W1593239840","https://openalex.org/W1972677112","https://openalex.org/W2520019424","https://openalex.org/W2139725124","https://openalex.org/W2801171064","https://openalex.org/W2541478194","https://openalex.org/W3034237830","https://openalex.org/W2105402874","https://openalex.org/W2306538696","https://openalex.org/W2962708371","https://openalex.org/W2962706858","https://openalex.org/W2401389395","https://openalex.org/W2899420204"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3,35,44],"introduce":[4],"a":[5],"new":[6],"approach":[7,68],"for":[8],"learning":[9],"language":[10,47,61],"models":[11,48,72],"by":[12],"training":[13],"them":[14],"to":[15,41,53,89],"estimate":[16],"word-context":[17],"pointwise":[18],"mutual":[19],"information":[20],"(PMI),":[21],"and":[22],"then":[23],"deriving":[24],"the":[25,54,76],"desired":[26],"conditional":[27],"probabilities":[28],"from":[29],"PMI":[30],"at":[31],"test":[32],"time.":[33],"Specifically,":[34],"show":[36],"that":[37,49,70,83],"with":[38,75],"minor":[39],"modifications":[40],"word2vec's":[42],"algorithm,":[43],"get":[45],"principled":[46],"are":[50,73],"closely":[51],"related":[52],"well-established":[55],"Noise":[56],"Contrastive":[57],"Estimation":[58],"(NCE)":[59],"based":[60],"models.":[62],"A":[63],"compelling":[64],"aspect":[65],"of":[66],"our":[67,71],"is":[69,84],"trained":[74],"same":[77],"simple":[78],"negative":[79],"sampling":[80],"objective":[81],"function":[82],"commonly":[85],"used":[86],"in":[87],"word2vec":[88],"learn":[90],"word":[91],"embeddings.":[92]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}