{"id":"https://openalex.org/W2970252926","doi":"https://doi.org/10.18653/v1/w19-4610","title":"Constrained Sequence-to-sequence Semitic Root Extraction for Enriching Word Embeddings","display_name":"Constrained Sequence-to-sequence Semitic Root Extraction for Enriching Word Embeddings","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970252926","doi":"https://doi.org/10.18653/v1/w19-4610","mag":"2970252926"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-4610","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4610","pdf_url":"https://www.aclweb.org/anthology/W19-4610.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 Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-4610.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035119055","display_name":"Ahmed El-Kishky","orcid":"https://orcid.org/0000-0003-0121-7781"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ahmed El-Kishky","raw_affiliation_strings":["Department of Computer Science, The University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102854017","display_name":"Xingyu Fu","orcid":"https://orcid.org/0000-0002-2649-8535"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xingyu Fu","raw_affiliation_strings":["Department of Computer Science, The University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034426215","display_name":"Aseel Addawood","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aseel Addawood","raw_affiliation_strings":["Department of Computer Science, The University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016018855","display_name":"Nahil Sobh","orcid":"https://orcid.org/0000-0001-6952-3465"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nahil Sobh","raw_affiliation_strings":["Department of Computer Science, The University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009361768","display_name":"Clare R. Voss","orcid":"https://orcid.org/0000-0001-5023-6474"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clare Voss","raw_affiliation_strings":["Computational & Information Sciences Directorate, Army Research Laboratory  Urbana, IL, USA,  Adelphi, MD, USA","Computational & Information Sciences Directorate, Army Research Laboratory \u2020 Urbana, IL, USA, \u2021 Adelphi, MD, USA"],"affiliations":[{"raw_affiliation_string":"Computational & Information Sciences Directorate, Army Research Laboratory  Urbana, IL, USA,  Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128"]},{"raw_affiliation_string":"Computational & Information Sciences Directorate, Army Research Laboratory \u2020 Urbana, IL, USA, \u2021 Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019539533","display_name":"Jiawei Han","orcid":"https://orcid.org/0000-0002-3629-2696"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Han","raw_affiliation_strings":["Department of Computer Science, The University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5035119055"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.42,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71001305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"88","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/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/T12031","display_name":"Speech and dialogue systems","score":0.9969000220298767,"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/morpheme","display_name":"Morpheme","score":0.7941393852233887},{"id":"https://openalex.org/keywords/root","display_name":"Root (linguistics)","score":0.7586938142776489},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7575714588165283},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7175174355506897},{"id":"https://openalex.org/keywords/semitic-languages","display_name":"Semitic languages","score":0.6956997513771057},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6949238777160645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.642000138759613},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6094608306884766},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4657759368419647},{"id":"https://openalex.org/keywords/interleaving","display_name":"Interleaving","score":0.45110028982162476},{"id":"https://openalex.org/keywords/word-formation","display_name":"Word formation","score":0.41225171089172363},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21526119112968445},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.1398974061012268},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13646864891052246}],"concepts":[{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.7941393852233887},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.7586938142776489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7575714588165283},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7175174355506897},{"id":"https://openalex.org/C132165367","wikidata":"https://www.wikidata.org/wiki/Q34049","display_name":"Semitic languages","level":3,"score":0.6956997513771057},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6949238777160645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.642000138759613},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6094608306884766},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4657759368419647},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.45110028982162476},{"id":"https://openalex.org/C2777509023","wikidata":"https://www.wikidata.org/wiki/Q327358","display_name":"Word formation","level":2,"score":0.41225171089172363},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21526119112968445},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.1398974061012268},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13646864891052246},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w19-4610","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4610","pdf_url":"https://www.aclweb.org/anthology/W19-4610.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 Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-4610","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4610","pdf_url":"https://www.aclweb.org/anthology/W19-4610.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 Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970252926.pdf","grobid_xml":"https://content.openalex.org/works/W2970252926.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W45352729","https://openalex.org/W1562769351","https://openalex.org/W1832693441","https://openalex.org/W1902237438","https://openalex.org/W1924770834","https://openalex.org/W1996824467","https://openalex.org/W2033937535","https://openalex.org/W2054997212","https://openalex.org/W2069917620","https://openalex.org/W2130942839","https://openalex.org/W2134164292","https://openalex.org/W2143088725","https://openalex.org/W2144810223","https://openalex.org/W2147272182","https://openalex.org/W2172279581","https://openalex.org/W2179974023","https://openalex.org/W2493363349","https://openalex.org/W2493916176","https://openalex.org/W2606676075","https://openalex.org/W2611127994","https://openalex.org/W2740654950","https://openalex.org/W2807354286","https://openalex.org/W2883158411","https://openalex.org/W2963877622","https://openalex.org/W3102682512"],"related_works":["https://openalex.org/W2466768907","https://openalex.org/W2220886357","https://openalex.org/W2791858227","https://openalex.org/W2075530739","https://openalex.org/W2586399803","https://openalex.org/W2361481624","https://openalex.org/W2105737024","https://openalex.org/W2152558769","https://openalex.org/W4280575942","https://openalex.org/W2080695183"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,95,125],"tackle":[4],"the":[5,13,29,41,70,79,82],"problem":[6,32],"of":[7,73,88,112],"\"root":[8],"extraction\"":[9],"from":[10,35],"words":[11,80],"in":[12,19,50],"Semitic":[14],"language":[15,22,135],"family.":[16],"A":[17],"challenge":[18],"applying":[20],"natural":[21],"processing":[23],"techniques":[24],"to":[25],"these":[26],"languages":[27],"is":[28,43],"data":[30],"sparsity":[31],"that":[33],"arises":[34],"their":[36],"rich":[37],"internal":[38,83],"morphology,":[39],"where":[40],"substructure":[42],"inherently":[44],"non-concatenative":[45],"and":[46,81,90,134],"morphemes":[47],"are":[48],"interdigitated":[49],"word":[51,120,130,132],"formation.":[52],"While":[53],"previous":[54],"automated":[55],"methods":[56,113],"have":[57,66],"relied":[58],"on":[59,129],"human-curated":[60],"rules":[61],"or":[62],"multiclass":[63],"classification,":[64],"they":[65],"not":[67],"fully":[68],"leveraged":[69],"various":[71],"combinations":[72],"regular,":[74],"sequential":[75],"concatenative":[76],"morphology":[77],"within":[78,85],"interleaving":[84],"templatic":[86],"stems":[87],"roots":[89],"patterns.":[91],"To":[92],"address":[93],"this,":[94],"propose":[96],"a":[97,110],"constrained":[98,107],"sequence-tosequence":[99],"root":[100,115],"extraction":[101],"method.":[102],"Experimental":[103],"results":[104,128],"show":[105,126],"our":[106],"model":[108],"outperforms":[109],"variety":[111],"at":[114],"extraction.":[116],"Furthermore,":[117],"by":[118],"enriching":[119],"embeddings":[121],"with":[122],"resulting":[123],"decompositions,":[124],"improved":[127],"analogy,":[131],"similarity,":[133],"modeling":[136],"tasks.":[137]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}