{"id":"https://openalex.org/W2890328620","doi":"https://doi.org/10.18653/v1/d18-1097","title":"Utilizing Character and Word Embeddings for Text Normalization with Sequence-to-Sequence Models","display_name":"Utilizing Character and Word Embeddings for Text Normalization with Sequence-to-Sequence Models","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2890328620","doi":"https://doi.org/10.18653/v1/d18-1097","mag":"2890328620"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1097","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1097","pdf_url":"https://www.aclweb.org/anthology/D18-1097.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 2018 Conference on Empirical Methods in Natural 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/D18-1097.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102331289","display_name":"Daniel Watson","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Watson","raw_affiliation_strings":["Computational Approaches to Modeling Language Lab New York University Abu Dhabi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Approaches to Modeling Language Lab New York University Abu Dhabi","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089887413","display_name":"Nasser Zalmout","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nasser Zalmout","raw_affiliation_strings":["Computational Approaches to Modeling Language Lab New York University Abu Dhabi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Approaches to Modeling Language Lab New York University Abu Dhabi","institution_ids":["https://openalex.org/I57206974"]}]},{"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/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nizar Habash","raw_affiliation_strings":["Computational Approaches to Modeling Language Lab New York University Abu Dhabi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Approaches to Modeling Language Lab New York University Abu Dhabi","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"837","last_page":"843"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9883999824523926,"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/computer-science","display_name":"Computer science","score":0.8334197998046875},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7262151837348938},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7182552218437195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6985867023468018},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6254675984382629},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5266594290733337},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5117003917694092},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5054259300231934},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.49632030725479126},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4838961064815521},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.47437673807144165},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.4354829788208008},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1796969473361969}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8334197998046875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7262151837348938},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7182552218437195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6985867023468018},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6254675984382629},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5266594290733337},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5117003917694092},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5054259300231934},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.49632030725479126},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4838961064815521},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.47437673807144165},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.4354829788208008},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1796969473361969},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1097","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1097","pdf_url":"https://www.aclweb.org/anthology/D18-1097.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1097","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1097","pdf_url":"https://www.aclweb.org/anthology/D18-1097.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313203","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821"},{"id":"https://openalex.org/F4320319918","display_name":"York University","ror":"https://ror.org/05fq50484"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2890328620.pdf","grobid_xml":"https://content.openalex.org/works/W2890328620.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W14596243","https://openalex.org/W99445809","https://openalex.org/W408046128","https://openalex.org/W648786980","https://openalex.org/W1522301498","https://openalex.org/W1610818344","https://openalex.org/W1902237438","https://openalex.org/W2012804051","https://openalex.org/W2016589492","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2147272182","https://openalex.org/W2153579005","https://openalex.org/W2157331557","https://openalex.org/W2250414785","https://openalex.org/W2250504723","https://openalex.org/W2250751111","https://openalex.org/W2250816155","https://openalex.org/W2251363456","https://openalex.org/W2251851155","https://openalex.org/W2251944986","https://openalex.org/W2321916036","https://openalex.org/W2470324779","https://openalex.org/W2493916176","https://openalex.org/W2525778437","https://openalex.org/W2737886250","https://openalex.org/W2757376562","https://openalex.org/W2799060650","https://openalex.org/W2804967932","https://openalex.org/W2893707415","https://openalex.org/W2952972707","https://openalex.org/W2962739339","https://openalex.org/W2963042536","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W3089057597","https://openalex.org/W4294170691","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W2160451571","https://openalex.org/W2495256954","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Text":[0],"normalization":[1],"is":[2],"an":[3,78],"important":[4],"enabling":[5],"technology":[6],"for":[7,98,117],"several":[8],"NLP":[9],"tasks.":[10],"Recently,":[11],"neural-network-based":[12],"approaches":[13],"have":[14],"outperformed":[15],"well-established":[16],"models":[17,82],"in":[18,22,32,66],"this":[19,33],"task.":[20],"However,":[21],"languages":[23],"other":[24],"than":[25],"English,":[26],"there":[27],"has":[28],"been":[29],"little":[30],"exploration":[31],"direction.":[34],"Both":[35],"the":[36,42,45,48,51,87,109,115,118],"scarcity":[37],"of":[38,44,50],"annotated":[39],"data":[40],"and":[41],"complexity":[43],"language":[46,133],"increase":[47],"difficulty":[49],"problem.":[52],"To":[53],"address":[54],"these":[55],"challenges,":[56],"we":[57],"use":[58],"a":[59,124,130],"sequence-to-sequence":[60],"model":[61,89,110],"with":[62,77,90,111],"character-based":[63],"attention,":[64],"which":[65],"addition":[67],"to":[68,92,122],"its":[69],"self-learned":[70],"character":[71],"embeddings,":[72],"uses":[73],"word":[74],"embeddings":[75],"pre-trained":[76],"approach":[79,121],"that":[80,107],"also":[81],"subword":[83],"information.":[84],"This":[85],"provides":[86],"neural":[88,119],"access":[91],"more":[93],"linguistic":[94],"information":[95],"especially":[96],"suitable":[97],"text":[99],"normalization,":[100],"without":[101],"large":[102],"parallel":[103],"corpora.":[104],"We":[105],"show":[106],"providing":[108],"word-level":[112],"features":[113],"bridges":[114],"gap":[116],"network":[120],"achieve":[123],"state-of-the-art":[125],"F":[126],"1":[127],"score":[128],"on":[129],"standard":[131],"Arabic":[132],"correction":[134],"shared":[135],"task":[136],"dataset.":[137]},"counts_by_year":[{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}