{"id":"https://openalex.org/W2563772108","doi":"https://doi.org/10.18653/v1/d16-1113","title":"Robust Gram Embeddings","display_name":"Robust Gram Embeddings","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2563772108","doi":"https://doi.org/10.18653/v1/d16-1113","mag":"2563772108"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d16-1113","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1113","pdf_url":"https://www.aclweb.org/anthology/D16-1113.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 2016 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D16-1113.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025690650","display_name":"Taygun Keke\u00e7","orcid":"https://orcid.org/0000-0001-6290-4732"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Taygun Kekec","raw_affiliation_strings":["Pattern Recognition and Bioinformatics Laboratory Delft University of Technology Delft, 2628CD, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Bioinformatics Laboratory Delft University of Technology Delft, 2628CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001295629","display_name":"David M. J. Tax","orcid":"https://orcid.org/0000-0002-5153-9087"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"David M. J. Tax","raw_affiliation_strings":["Pattern Recognition and Bioinformatics Laboratory Delft University of Technology Delft, 2628CD, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Bioinformatics Laboratory Delft University of Technology Delft, 2628CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5025690650"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1060","last_page":"1065"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9894000291824341,"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/overfitting","display_name":"Overfitting","score":0.9556031823158264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7090380191802979},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6899282336235046},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6874906420707703},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6840183734893799},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6733676791191101},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.666262686252594},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6373059153556824},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6037623286247253},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5714321732521057},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5713852643966675},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5250052213668823},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5049427151679993},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.44417107105255127},{"id":"https://openalex.org/keywords/gram","display_name":"Gram","score":0.41933512687683105},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3807942569255829},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3804089426994324},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.23047158122062683},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2023756206035614},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.08421549201011658}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9556031823158264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7090380191802979},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6899282336235046},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6874906420707703},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6840183734893799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6733676791191101},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.666262686252594},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6373059153556824},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6037623286247253},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5714321732521057},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5713852643966675},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5250052213668823},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5049427151679993},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.44417107105255127},{"id":"https://openalex.org/C161369605","wikidata":"https://www.wikidata.org/wiki/Q41803","display_name":"Gram","level":3,"score":0.41933512687683105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3807942569255829},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3804089426994324},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.23047158122062683},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2023756206035614},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.08421549201011658},{"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},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d16-1113","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1113","pdf_url":"https://www.aclweb.org/anthology/D16-1113.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 2016 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d16-1113","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1113","pdf_url":"https://www.aclweb.org/anthology/D16-1113.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 2016 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2412543723","display_name":null,"funder_award_id":"612.001.301","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2563772108.pdf","grobid_xml":"https://content.openalex.org/works/W2563772108.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1491334865","https://openalex.org/W1492459858","https://openalex.org/W1495323440","https://openalex.org/W1499253590","https://openalex.org/W1614298861","https://openalex.org/W1662133657","https://openalex.org/W1966096622","https://openalex.org/W2097732278","https://openalex.org/W2111597839","https://openalex.org/W2113459411","https://openalex.org/W2122825543","https://openalex.org/W2125031621","https://openalex.org/W2138204974","https://openalex.org/W2170682101","https://openalex.org/W2250480277","https://openalex.org/W2251803266","https://openalex.org/W2252211741","https://openalex.org/W2295508206","https://openalex.org/W2949441331","https://openalex.org/W2950133940","https://openalex.org/W2951943225","https://openalex.org/W3006431365","https://openalex.org/W4294170691","https://openalex.org/W4298045075","https://openalex.org/W4365799834"],"related_works":["https://openalex.org/W2906970013","https://openalex.org/W3126081632","https://openalex.org/W2625039379","https://openalex.org/W2088254117","https://openalex.org/W3208882810","https://openalex.org/W4254593385","https://openalex.org/W2790582133","https://openalex.org/W1901380241","https://openalex.org/W311963822","https://openalex.org/W2972862903"],"abstract_inverted_index":{"Word":[0],"embedding":[1,46],"models":[2,23,35],"learn":[3],"vectorial":[4],"word":[5,100],"representations":[6],"that":[7,68],"can":[8],"be":[9],"used":[10],"in":[11,86,96],"a":[12,44,97],"variety":[13],"of":[14,33,99],"NLP":[15],"applications.":[16],"When":[17],"training":[18,88],"data":[19],"is":[20,81],"scarce,":[21],"these":[22],"risk":[24],"losing":[25],"their":[26],"generalization":[27],"abilities":[28],"due":[29],"to":[30,39,79,84,93],"the":[31,34,37,57,69,87],"complexity":[32],"and":[36,61,90],"overfitting":[38,54],"finite":[40],"data.":[41],"We":[42],"propose":[43],"regularized":[45],"formulation,":[47],"called":[48],"Robust":[49],"Gram":[50],"(RG),":[51],"which":[52],"penalizes":[53],"by":[55],"suppressing":[56],"disparity":[58],"between":[59],"target":[60],"context":[62],"embeddings.":[63],"Our":[64],"experimental":[65],"analysis":[66],"shows":[67],"RG":[70],"model":[71],"trained":[72],"on":[73],"small":[74],"datasets":[75],"generalizes":[76],"better":[77],"compared":[78],"alternatives,":[80],"more":[82],"robust":[83],"variations":[85],"set,":[89],"correlates":[91],"well":[92],"human":[94],"similarities":[95],"set":[98],"similarity":[101],"tasks.":[102]},"counts_by_year":[{"year":2019,"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"}