{"id":"https://openalex.org/W3113532658","doi":"https://doi.org/10.18653/v1/2020.coling-main.412","title":"Utilizing Subword Entities in Character-Level Sequence-to-Sequence Lemmatization Models","display_name":"Utilizing Subword Entities in Character-Level Sequence-to-Sequence Lemmatization Models","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3113532658","doi":"https://doi.org/10.18653/v1/2020.coling-main.412","mag":"3113532658"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.coling-main.412","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.412","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.412.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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/2020.coling-main.412.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089887413","display_name":"Nasser Zalmout","orcid":null},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":true,"raw_author_name":"Nasser Zalmout","raw_affiliation_strings":["Computational Approaches to Modeling Language (CAMeL) Lab New York University Abu Dhabi United Arab Emirates"],"affiliations":[{"raw_affiliation_string":"Computational Approaches to Modeling Language (CAMeL) Lab New York University Abu Dhabi United Arab Emirates","institution_ids":["https://openalex.org/I120250893"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084517393","display_name":"Nizar Habash","orcid":"https://orcid.org/0000-0002-1831-3457"},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Nizar Habash","raw_affiliation_strings":["Computational Approaches to Modeling Language (CAMeL) Lab New York University Abu Dhabi United Arab Emirates"],"affiliations":[{"raw_affiliation_string":"Computational Approaches to Modeling Language (CAMeL) Lab New York University Abu Dhabi United Arab Emirates","institution_ids":["https://openalex.org/I120250893"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5089887413"],"corresponding_institution_ids":["https://openalex.org/I120250893"],"apc_list":null,"apc_paid":null,"fwci":0.1326,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56982166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4676","last_page":"4682"},"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":0.9997000098228455,"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/T13629","display_name":"Text Readability and Simplification","score":0.9750999808311462,"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/lemmatisation","display_name":"Lemmatisation","score":0.7745543718338013},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7373732328414917},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6894350647926331},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6610317230224609},{"id":"https://openalex.org/keywords/lemma","display_name":"Lemma (botany)","score":0.6451390981674194},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6204614639282227},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5418487787246704},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5241739749908447},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.5173146724700928},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48345765471458435},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.44062015414237976},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4160703122615814},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16330894827842712},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.11077845096588135},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08017200231552124},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06256940960884094}],"concepts":[{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.7745543718338013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7373732328414917},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6894350647926331},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6610317230224609},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.6451390981674194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6204614639282227},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5418487787246704},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5241739749908447},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.5173146724700928},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48345765471458435},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.44062015414237976},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4160703122615814},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16330894827842712},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.11077845096588135},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08017200231552124},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06256940960884094},{"id":"https://openalex.org/C46757340","wikidata":"https://www.wikidata.org/wiki/Q43238","display_name":"Poaceae","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2020.coling-main.412","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.412","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.412.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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.coling-main.412","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.412","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.412.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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3113532658.pdf","grobid_xml":"https://content.openalex.org/works/W3113532658.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1522301498","https://openalex.org/W1582588624","https://openalex.org/W1598638450","https://openalex.org/W1883682364","https://openalex.org/W1902237438","https://openalex.org/W2099162170","https://openalex.org/W2125768350","https://openalex.org/W2126784811","https://openalex.org/W2153579005","https://openalex.org/W2168579166","https://openalex.org/W2250648475","https://openalex.org/W2250816155","https://openalex.org/W2251386579","https://openalex.org/W2295375623","https://openalex.org/W2401109438","https://openalex.org/W2493916176","https://openalex.org/W2757376562","https://openalex.org/W2799072540","https://openalex.org/W2804387108","https://openalex.org/W2950333634","https://openalex.org/W2960637190","https://openalex.org/W2963714641","https://openalex.org/W2963876447","https://openalex.org/W2964121744","https://openalex.org/W3029683630","https://openalex.org/W3183153947","https://openalex.org/W4252362825","https://openalex.org/W4294170691","https://openalex.org/W4394651511"],"related_works":["https://openalex.org/W1561563106","https://openalex.org/W2116831595","https://openalex.org/W2884860922","https://openalex.org/W3042025871","https://openalex.org/W2226076398","https://openalex.org/W2891344292","https://openalex.org/W2251336637","https://openalex.org/W4289548496","https://openalex.org/W1562768541","https://openalex.org/W2807614063"],"abstract_inverted_index":{"In":[0,17],"this":[1],"paper":[2],"we":[3,25],"present":[4,38],"a":[5,59,101],"character-level":[6],"sequence-to-sequence":[7],"lemmatization":[8],"model,":[9],"utilizing":[10],"several":[11,39],"subword":[12],"features":[13,44],"in":[14,123],"multiple":[15],"configurations.":[16],"addition":[18],"to":[19,92,115],"generic":[20,69],"n-gram":[21,70],"embeddings":[22,71],"(using":[23],"FastText),":[24],"experiment":[26],"with":[27,58,90],"concatenative":[28],"(stems)":[29],"and":[30,33,84,94],"templatic":[31],"(roots":[32],"patterns)":[34],"morphological":[35],"subwords.":[36,78],"We":[37,79],"architectures":[40],"that":[41,66,108,119],"embed":[42],"these":[43],"directly":[45],"at":[46,54],"the":[47,55,68,75,124],"encoder":[48],"side,":[49],"or":[50],"learn":[51],"them":[52],"jointly":[53],"decoder":[56],"side":[57],"multitask":[60],"learning":[61],"architecture.":[62],"The":[63],"results":[64],"indicate":[65],"using":[67],"(through":[72],"FastText)":[73],"outperform":[74],"other":[76],"linguistically-driven":[77],"use":[80],"Modern":[81],"Standard":[82],"Arabic":[83,86],"Egyptian":[85],"as":[87],"test":[88],"cases,":[89],"up":[91],"22%":[93],"13%":[95],"relative":[96],"error":[97,105],"reduction,":[98],"respectively,":[99],"from":[100],"strong":[102],"baseline.":[103],"An":[104],"analysis":[106],"shows":[107],"our":[109],"best":[110],"system":[111],"is":[112],"even":[113],"able":[114],"handle":[116],"word/lemma":[117],"pairs":[118],"are":[120],"both":[121],"unseen":[122],"training":[125],"data.":[126]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}