{"id":"https://openalex.org/W4415887449","doi":"https://doi.org/10.18653/v1/2019.gwc-1.18","title":"Synthetic, yet natural: Properties of WordNet random walk corpora and the impact of rare words on embedding performance","display_name":"Synthetic, yet natural: Properties of WordNet random walk corpora and the impact of rare words on embedding performance","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W4415887449","doi":"https://doi.org/10.18653/v1/2019.gwc-1.18"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2019.gwc-1.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2019.gwc-1.18","pdf_url":"https://aclanthology.org/2019.gwc-1.18.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 10th Global Wordnet Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2019.gwc-1.18.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057328421","display_name":"Filip Klubi\u010dka","orcid":"https://orcid.org/0000-0001-9712-6141"},"institutions":[{"id":"https://openalex.org/I168346926","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38","country_code":"IE","type":"nonprofit","lineage":["https://openalex.org/I168346926"]},{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Filip Klubi\u010dka","raw_affiliation_strings":["ADAPT Centre , Dublin , Ireland","Technological University Dublin , Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ADAPT Centre , Dublin , Ireland","institution_ids":["https://openalex.org/I168346926"]},{"raw_affiliation_string":"Technological University Dublin , Ireland","institution_ids":["https://openalex.org/I4210144925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034969780","display_name":"Alfredo Maldonado","orcid":"https://orcid.org/0000-0001-8426-5249"},"institutions":[{"id":"https://openalex.org/I168346926","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38","country_code":"IE","type":"nonprofit","lineage":["https://openalex.org/I168346926"]},{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Alfredo Maldonado","raw_affiliation_strings":["ADAPT Centre , Dublin , Ireland","Trinity College Dublin , Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ADAPT Centre , Dublin , Ireland","institution_ids":["https://openalex.org/I168346926"]},{"raw_affiliation_string":"Trinity College Dublin , Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086319818","display_name":"Abhijit Mahalunkar","orcid":"https://orcid.org/0000-0001-5795-8728"},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Abhijit Mahalunkar","raw_affiliation_strings":["Technological University Dublin , Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technological University Dublin , Ireland","institution_ids":["https://openalex.org/I4210144925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079991004","display_name":"John D. Kelleher","orcid":"https://orcid.org/0000-0001-6462-3248"},"institutions":[{"id":"https://openalex.org/I168346926","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38","country_code":"IE","type":"nonprofit","lineage":["https://openalex.org/I168346926"]},{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"John Kelleher","raw_affiliation_strings":["ADAPT Centre , Dublin , Ireland","Technological University Dublin , Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ADAPT Centre , Dublin , Ireland","institution_ids":["https://openalex.org/I168346926"]},{"raw_affiliation_string":"Technological University Dublin , Ireland","institution_ids":["https://openalex.org/I4210144925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28902767,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"140","last_page":"150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.26190000772476196,"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":0.26190000772476196,"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":0.2143000066280365,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.06989999860525131,"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/random-walk","display_name":"Random walk","score":0.6547999978065491},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.5740000009536743},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5544999837875366},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.33959999680519104},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.2777000069618225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6668000221252441},{"id":"https://openalex.org/C121194460","wikidata":"https://www.wikidata.org/wiki/Q856741","display_name":"Random walk","level":2,"score":0.6547999978065491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6258000135421753},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5968000292778015},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.5740000009536743},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5544999837875366},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.33959999680519104},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2678000032901764}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2019.gwc-1.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2019.gwc-1.18","pdf_url":"https://aclanthology.org/2019.gwc-1.18.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 10th Global Wordnet Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2019.gwc-1.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2019.gwc-1.18","pdf_url":"https://aclanthology.org/2019.gwc-1.18.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 10th Global Wordnet Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2563910032","display_name":null,"funder_award_id":"13/RC/2106","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G3993907298","display_name":"ADAPT: Centre for Digital Content Platform Research","funder_award_id":"13/RC/2106","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415887449.pdf","grobid_xml":"https://content.openalex.org/works/W4415887449.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Creating":[0],"word":[1,55,132],"embeddings":[2,130],"that":[3,95,116],"reflect":[4],"semantic":[5],"relationships":[6],"encoded":[7],"in":[8,98,104,122],"lexical":[9],"knowledge":[10,25,45],"resources":[11],"is":[12,17],"an":[13],"open":[14],"challenge.One":[15],"approach":[16],"to":[18,27,35,68],"use":[19,32,64],"a":[20,24,29,77,123],"random":[21],"walk":[22],"over":[23],"graph":[26,46],"generate":[28],"pseudocorpus":[30],"and":[31,51,87,110,113],"this":[33],"corpus":[34],"train":[36],"embeddings.However,":[37],"the":[38,41,44,48,53,69,74,81,84,91,96,99,117,126],"effect":[39],"of":[40,43,73,83,119,128],"shape":[42],"on":[47,52,90,131],"generated":[49,85],"pseudo-corpora,":[50,86],"resulting":[54,92],"embeddings,":[56],"has":[57],"not":[58],"been":[59],"studied.To":[60],"explore":[61],"this,":[62],"we":[63],"English":[65],"WordNet,":[66],"constrained":[67],"taxonomic":[70],"(tree-like)":[71],"portion":[72],"graph,":[75],"as":[76,108],"case":[78],"study.We":[79],"investigate":[80],"properties":[82,102],"their":[88],"impact":[89],"embeddings.We":[93],"find":[94],"distributions":[97],"psuedo-corpora":[100],"exhibit":[101],"found":[103],"natural":[105],"corpora,":[106],"such":[107],"Zipf's":[109],"Heaps'":[111],"law,":[112],"also":[114],"observe":[115],"proportion":[118],"rare":[120],"words":[121],"pseudo-corpus":[124],"affects":[125],"performance":[127],"its":[129],"similarity.":[133]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}