{"id":"https://openalex.org/W2952405470","doi":"https://doi.org/10.18653/v1/p19-3032","title":"MoNoise: A Multi-lingual and Easy-to-use Lexical Normalization Tool","display_name":"MoNoise: A Multi-lingual and Easy-to-use Lexical Normalization Tool","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2952405470","doi":"https://doi.org/10.18653/v1/p19-3032","mag":"2952405470"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-3032","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-3032","pdf_url":"https://www.aclweb.org/anthology/P19-3032.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 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-3032.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039811894","display_name":"Rob van der Goot","orcid":"https://orcid.org/0009-0003-1999-4156"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Rob van der Goot","raw_affiliation_strings":["Center for Language and Cognition","University of Groningen"],"affiliations":[{"raw_affiliation_string":"Center for Language and Cognition","institution_ids":[]},{"raw_affiliation_string":"University of Groningen","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5039811894"],"corresponding_institution_ids":["https://openalex.org/I169381384"],"apc_list":null,"apc_paid":null,"fwci":3.3231,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.93897494,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"201","last_page":"206"},"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":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"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":0.8682588338851929},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.864580512046814},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5586701035499573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5386818051338196},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.50380939245224},{"id":"https://openalex.org/keywords/source-lines-of-code","display_name":"Source lines of code","score":0.48657047748565674},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34798163175582886},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.34359633922576904},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.18972447514533997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8682588338851929},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.864580512046814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5586701035499573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5386818051338196},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.50380939245224},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.48657047748565674},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34798163175582886},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34359633922576904},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.18972447514533997},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/p19-3032","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-3032","pdf_url":"https://www.aclweb.org/anthology/P19-3032.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 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/495b050b-b003-40e9-8ce3-155e684fd4ad","is_oa":false,"landing_page_url":"https://research.rug.nl/en/publications/495b050b-b003-40e9-8ce3-155e684fd4ad","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"van der Goot , R 2019 , ' MoNoise : A Multi-lingual and Easy-to-use Lexical Normalization Tool ' , Paper presented at 57th Annual Meeting of the Association for Computational Linguistics (ACL) , Florence , Italy , 28/07/2019 - 02/08/2019 .","raw_type":"conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-3032","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-3032","pdf_url":"https://www.aclweb.org/anthology/P19-3032.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 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320319634","display_name":"Nuance Foundation","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952405470.pdf","grobid_xml":"https://content.openalex.org/works/W2952405470.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W168564468","https://openalex.org/W1593203598","https://openalex.org/W1614298861","https://openalex.org/W2125270091","https://openalex.org/W2146867136","https://openalex.org/W2172112754","https://openalex.org/W2180008620","https://openalex.org/W2250174865","https://openalex.org/W2250423567","https://openalex.org/W2250729567","https://openalex.org/W2250863007","https://openalex.org/W2296474619","https://openalex.org/W2371227879","https://openalex.org/W2397119265","https://openalex.org/W2621251601","https://openalex.org/W2760845412","https://openalex.org/W2783407300","https://openalex.org/W2806391156","https://openalex.org/W2916050641","https://openalex.org/W2940696931","https://openalex.org/W2963386475","https://openalex.org/W2963626623","https://openalex.org/W2982630078"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2591697403","https://openalex.org/W4246352526","https://openalex.org/W2121910908"],"abstract_inverted_index":{"In":[0],"this":[1,31],"paper,":[2],"we":[3,49,92],"introduce":[4],"and":[5,103],"demonstrate":[6],"the":[7,13,37,51,94,98,101,106],"online":[8,121],"demo":[9,122],"as":[10,12],"well":[11],"command":[14],"line":[15],"interface":[16],"of":[17,26,53,86,88,100],"a":[18,24,61,66,79,115],"lexical":[19],"normalization":[20,42],"system":[21],"(MoNoise)":[22],"for":[23,40,74,83],"variety":[25],"languages.":[27],"We":[28],"further":[29],"improve":[30],"model":[32,107],"by":[33],"using":[34],"features":[35],"from":[36],"original":[38],"word":[39],"every":[41],"candidate.":[43],"For":[44],"comparison":[45],"with":[46,65,113],"future":[47],"work,":[48],"propose":[50],"bundling":[52],"seven":[54,87],"datasets":[55],"in":[56,118],"six":[57,84],"languages":[58],"to":[59,96],"form":[60],"new":[62,80],"benchmark,":[63],"together":[64],"novel":[67],"evaluation":[68],"metric":[69],"which":[70],"is":[71],"particularly":[72],"suitable":[73],"cross-dataset":[75],"comparisons.":[76],"MoNoise":[77],"reaches":[78],"state-of-art":[81],"performance":[82],"out":[85],"these":[89],"datasets.":[90],"Furthermore,":[91],"allow":[93],"user":[95],"tune":[97],"'aggressiveness'":[99],"normalization,":[102],"show":[104],"how":[105],"can":[108,123],"be":[109,124],"made":[110],"more":[111],"efficient":[112],"only":[114],"small":[116],"loss":[117],"performance.":[119],"The":[120],"found":[125],"on:":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}