{"id":"https://openalex.org/W4391335451","doi":"https://doi.org/10.18653/v1/2024.latechclfl-1.26","title":"Pairing Orthographically Variant Literary Words to Standard Equivalents Using Neural Edit Distance Models","display_name":"Pairing Orthographically Variant Literary Words to Standard Equivalents Using Neural Edit Distance Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391335451","doi":"https://doi.org/10.18653/v1/2024.latechclfl-1.26"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.latechclfl-1.26","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.latechclfl-1.26","pdf_url":"https://aclanthology.org/2024.latechclfl-1.26.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 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.latechclfl-1.26.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093817186","display_name":"Craig Messner","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]},{"id":"https://openalex.org/I4210151848","display_name":"Johns Hopkins Center for Communication Programs","ror":"https://ror.org/05hs7zv85","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I145311948","https://openalex.org/I4210151848"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Craig Messner","raw_affiliation_strings":["Center for Digital Humanities Johns Hopkins University Center for Digital Humanities Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Digital Humanities Johns Hopkins University Center for Digital Humanities Johns Hopkins University","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424","https://openalex.org/I4210151848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046184426","display_name":"Tom Lippincott","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]},{"id":"https://openalex.org/I4210151848","display_name":"Johns Hopkins Center for Communication Programs","ror":"https://ror.org/05hs7zv85","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I145311948","https://openalex.org/I4210151848"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom Lippincott","raw_affiliation_strings":["Center for Digital Humanities Johns Hopkins University Center for Digital Humanities Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Digital Humanities Johns Hopkins University Center for Digital Humanities Johns Hopkins University","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424","https://openalex.org/I4210151848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"264","last_page":"269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9876999855041504,"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":0.9653000235557556,"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/pairing","display_name":"Pairing","score":0.8283895254135132},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5060016512870789},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5035807490348816},{"id":"https://openalex.org/keywords/equivalent","display_name":"Equivalent","score":0.48739200830459595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.456269234418869},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4514065682888031},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.40756916999816895},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3265792727470398},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13941112160682678},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08670729398727417}],"concepts":[{"id":"https://openalex.org/C14103023","wikidata":"https://www.wikidata.org/wiki/Q11681459","display_name":"Pairing","level":3,"score":0.8283895254135132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5060016512870789},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5035807490348816},{"id":"https://openalex.org/C131857375","wikidata":"https://www.wikidata.org/wiki/Q36384","display_name":"Equivalent","level":2,"score":0.48739200830459595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.456269234418869},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4514065682888031},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.40756916999816895},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3265792727470398},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13941112160682678},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08670729398727417},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C54101563","wikidata":"https://www.wikidata.org/wiki/Q124131","display_name":"Superconductivity","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2024.latechclfl-1.26","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.latechclfl-1.26","pdf_url":"https://aclanthology.org/2024.latechclfl-1.26.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 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2401.15068","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.15068","pdf_url":"https://arxiv.org/pdf/2401.15068","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2401.15068","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2401.15068","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.15068","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.latechclfl-1.26","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.latechclfl-1.26","pdf_url":"https://aclanthology.org/2024.latechclfl-1.26.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 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8899999856948853}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391335451.pdf","grobid_xml":"https://content.openalex.org/works/W4391335451.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3015473028","https://openalex.org/W3201176751","https://openalex.org/W2029180842","https://openalex.org/W2051379014","https://openalex.org/W2057898405","https://openalex.org/W2790938167","https://openalex.org/W2953807518","https://openalex.org/W1993094293","https://openalex.org/W2258335979","https://openalex.org/W2890366349"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,27,53,62],"novel":[3],"corpus":[4,63],"consisting":[5],"of":[6,13,29,46,52,55,64,77,83],"orthographically":[7],"variant":[8],"words":[9],"found":[10],"in":[11,80],"works":[12],"19":[14],"th":[15],"century":[16],"U.S.":[17],"literature":[18],"annotated":[19],"with":[20,38],"their":[21,39],"corresponding":[22],"\"standard\"":[23],"word":[24],"pair.We":[25],"train":[26],"set":[28,54],"neural":[30,56],"edit":[31,57],"distance":[32,58],"models":[33,48,59,79],"to":[34,49,102],"pair":[35],"these":[36,47,78],"variants":[37],"standard":[40],"forms,":[41],"and":[42,90],"compare":[43],"the":[44,50,74,81,95],"performance":[45,51,76],"trained":[60],"on":[61,94],"orthographic":[65,99],"errors":[66],"made":[67],"by":[68],"L2":[69],"English":[70],"learners.Finally,":[71],"we":[72],"analyze":[73],"relative":[75],"light":[82],"different":[84],"negative":[85],"training":[86],"sample":[87],"generation":[88],"strategies,":[89],"offer":[91],"concluding":[92],"remarks":[93],"unique":[96],"challenge":[97],"literary":[98],"variation":[100],"poses":[101],"string":[103],"pairing":[104],"methodologies.":[105]},"counts_by_year":[],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2024-01-30T00:00:00"}
