{"id":"https://openalex.org/W2250863007","doi":"https://doi.org/10.18653/v1/w15-4313","title":"NCSU-SAS-Ning: Candidate Generation and Feature Engineering for Supervised Lexical Normalization","display_name":"NCSU-SAS-Ning: Candidate Generation and Feature Engineering for Supervised Lexical Normalization","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2250863007","doi":"https://doi.org/10.18653/v1/w15-4313","mag":"2250863007"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-4313","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4313","pdf_url":"https://www.aclweb.org/anthology/W15-4313.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 Workshop on Noisy User-generated Text","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/W15-4313.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064463976","display_name":"Jin Ning","orcid":"https://orcid.org/0000-0002-8551-7038"},"institutions":[{"id":"https://openalex.org/I122754148","display_name":"SAS Institute (United States)","ror":"https://ror.org/01093z329","country_code":"US","type":"company","lineage":["https://openalex.org/I122754148"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ning Jin","raw_affiliation_strings":["Text Analytics R&D SAS Institute, Inc. Cary, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Text Analytics R&D SAS Institute, Inc. Cary, NC, USA","institution_ids":["https://openalex.org/I122754148"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5064463976"],"corresponding_institution_ids":["https://openalex.org/I122754148"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"87","last_page":"92"},"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":0.9983999729156494,"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":0.978600025177002,"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/normalization","display_name":"Normalization (sociology)","score":0.8736470937728882},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7680882215499878},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6907353401184082},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6148814558982849},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.5335382223129272},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4483826458454132},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32922154664993286},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.20485281944274902}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8736470937728882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7680882215499878},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6907353401184082},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6148814558982849},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.5335382223129272},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4483826458454132},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32922154664993286},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.20485281944274902},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w15-4313","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4313","pdf_url":"https://www.aclweb.org/anthology/W15-4313.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 Workshop on Noisy User-generated Text","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-4313","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4313","pdf_url":"https://www.aclweb.org/anthology/W15-4313.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 Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250863007.pdf","grobid_xml":"https://content.openalex.org/works/W2250863007.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W2071386227","https://openalex.org/W2086320398","https://openalex.org/W2121227244","https://openalex.org/W2146867136","https://openalex.org/W2157765050","https://openalex.org/W2250729567","https://openalex.org/W2911964244","https://openalex.org/W4233787372"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W4321441197","https://openalex.org/W2953716828","https://openalex.org/W2469820710","https://openalex.org/W2152642030"],"abstract_inverted_index":{"User":[0],"generated":[1],"content":[2],"often":[3],"contains":[4],"non-standard":[5],"words":[6],"that":[7],"hinder":[8],"effective":[9],"automatic":[10],"text":[11,74],"processing.":[12],"In":[13],"this":[14],"paper,":[15],"we":[16,20],"present":[17],"a":[18,39,47,58],"system":[19,56],"developed":[21],"to":[22],"perform":[23],"lexical":[24],"normalization":[25,75],"for":[26],"English":[27,73],"Twitter":[28],"text.":[29],"It":[30],"first":[31],"generates":[32],"candidates":[33],"based":[34],"on":[35],"past":[36],"knowledge":[37],"and":[38,44,61],"novel":[40],"string":[41],"similarity":[42],"measurement":[43],"then":[45],"selects":[46],"candidate":[48],"using":[49],"features":[50],"learned":[51],"from":[52],"training":[53],"data.":[54],"The":[55,65],"has":[57],"constrained":[59,66],"mode":[60,67],"an":[62],"unconstrained":[63],"mode.":[64],"participated":[68],"in":[69],"the":[70],"W-NUT":[71],"noisy":[72],"competition":[76]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}