{"id":"https://openalex.org/W2798485145","doi":"https://doi.org/10.18653/v1/p18-1220","title":"Multi-Input Attention for Unsupervised OCR Correction","display_name":"Multi-Input Attention for Unsupervised OCR Correction","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2798485145","doi":"https://doi.org/10.18653/v1/p18-1220","mag":"2798485145"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-1220","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1220","pdf_url":"https://www.aclweb.org/anthology/P18-1220.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-1220.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004378974","display_name":"Rui Dong","orcid":"https://orcid.org/0000-0002-4110-3976"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Rui Dong","raw_affiliation_strings":["Northeastern University","College of Computer Information and Science"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]},{"raw_affiliation_string":"College of Computer Information and Science","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101722493","display_name":"David A. Smith","orcid":"https://orcid.org/0000-0002-6636-6940"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"David Smith","raw_affiliation_strings":["College of Computer Information and Science","Northeastern University"],"affiliations":[{"raw_affiliation_string":"College of Computer Information and Science","institution_ids":[]},{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004378974"],"corresponding_institution_ids":["https://openalex.org/I87182695"],"apc_list":null,"apc_paid":null,"fwci":3.3848,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.93835797,"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":"2363","last_page":"2372"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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":0.995199978351593,"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":0.9951000213623047,"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":0.8044388890266418},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.777960479259491},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6604630947113037},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.6553133726119995},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.652975857257843},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5721630454063416},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5486149191856384},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5452079176902771},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5095015168190002},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4511517584323883},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.44693100452423096},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4120885729789734},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21376928687095642},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08533960580825806},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07920441031455994}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8044388890266418},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.777960479259491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6604630947113037},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.6553133726119995},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.652975857257843},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5721630454063416},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5486149191856384},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5452079176902771},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5095015168190002},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4511517584323883},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.44693100452423096},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4120885729789734},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21376928687095642},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08533960580825806},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07920441031455994},{"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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p18-1220","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1220","pdf_url":"https://www.aclweb.org/anthology/P18-1220.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-1220","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1220","pdf_url":"https://www.aclweb.org/anthology/P18-1220.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1974105159","display_name":null,"funder_award_id":"2R01DC009834","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6505806964","display_name":null,"funder_award_id":"DC009834","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6900692256","display_name":null,"funder_award_id":"2R01DC009834-06A1","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7265857034","display_name":null,"funder_award_id":"R01DC009834","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306146","display_name":"Andrew W. Mellon Foundation","ror":"https://ror.org/04jsh2530"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798485145.pdf","grobid_xml":"https://content.openalex.org/works/W2798485145.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1558807800","https://openalex.org/W1968290777","https://openalex.org/W1972016971","https://openalex.org/W1975679321","https://openalex.org/W1976978162","https://openalex.org/W1978022086","https://openalex.org/W2000447173","https://openalex.org/W2018840051","https://openalex.org/W2024348326","https://openalex.org/W2045566081","https://openalex.org/W2063828767","https://openalex.org/W2064675550","https://openalex.org/W2069189382","https://openalex.org/W2085922539","https://openalex.org/W2087064593","https://openalex.org/W2098967804","https://openalex.org/W2104543051","https://openalex.org/W2111558710","https://openalex.org/W2124990912","https://openalex.org/W2131774270","https://openalex.org/W2133564696","https://openalex.org/W2134800885","https://openalex.org/W2148036569","https://openalex.org/W2148752429","https://openalex.org/W2157331557","https://openalex.org/W2321916036","https://openalex.org/W2410156476","https://openalex.org/W2741009929","https://openalex.org/W2741223475","https://openalex.org/W2793452059","https://openalex.org/W2963407669","https://openalex.org/W2963721761","https://openalex.org/W2964034111","https://openalex.org/W2964036946","https://openalex.org/W2964308564","https://openalex.org/W3158986179","https://openalex.org/W4230543443","https://openalex.org/W4243754476","https://openalex.org/W4256120941","https://openalex.org/W4293361313"],"related_works":["https://openalex.org/W1534274833","https://openalex.org/W3117246195","https://openalex.org/W2361861616","https://openalex.org/W156620619","https://openalex.org/W2098233217","https://openalex.org/W2914363205","https://openalex.org/W2616249226","https://openalex.org/W2980068837","https://openalex.org/W2098872742","https://openalex.org/W2575782020"],"abstract_inverted_index":{"We":[0,61],"propose":[1],"a":[2,17,28,45,84],"novel":[3],"approach":[4],"to":[5,54,75],"OCR":[6],"post-correction":[7],"that":[8,98],"exploits":[9],"repeated":[10],"texts":[11],"in":[12,110],"large":[13],"corpora":[14,90],"both":[15],"as":[16,27],"source":[18,29],"of":[19,30,65,91,119],"noisy":[20],"target":[21],"outputs":[22],"for":[23,41,56],"unsupervised":[24,100],"training":[25,66,74],"and":[26,44,94,105],"evidence":[31],"when":[32],"decoding.":[33],"A":[34],"sequence-to-sequence":[35],"model":[36,69],"with":[37,48,116],"attention":[38,50],"is":[39,52],"applied":[40],"single-input":[42],"correction,":[43],"new":[46],"decoder":[47],"multi-input":[49,120],"averaging":[51],"developed":[53],"search":[55],"consensus":[57],"among":[58],"multiple":[59],"sequences.":[60],"design":[62],"two":[63,89],"ways":[64],"the":[67,103,117],"correction":[68],"without":[70],"human":[71],"annotation,":[72],"either":[73],"match":[76],"noisily":[77],"observed":[78],"textual":[79],"variants":[80],"or":[81],"bootstrapping":[82],"from":[83],"uniform":[85],"error":[86,107],"model.":[87],"On":[88],"historical":[92],"newspapers":[93],"books,":[95],"we":[96],"show":[97],"these":[99],"techniques":[101],"cut":[102],"character":[104],"word":[106],"rates":[108],"nearly":[109],"half":[111],"on":[112],"single":[113],"inputs":[114],"and,":[115],"addition":[118],"decoding,":[121],"can":[122],"rival":[123],"supervised":[124],"methods.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}