{"id":"https://openalex.org/W4319309557","doi":"https://doi.org/10.1109/skima57145.2022.10029532","title":"Encoder-Decoder Language Model for Khmer Handwritten Text Recognition in Historical Documents","display_name":"Encoder-Decoder Language Model for Khmer Handwritten Text Recognition in Historical Documents","publication_year":2022,"publication_date":"2022-12-02","ids":{"openalex":"https://openalex.org/W4319309557","doi":"https://doi.org/10.1109/skima57145.2022.10029532"},"language":"en","primary_location":{"id":"doi:10.1109/skima57145.2022.10029532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/skima57145.2022.10029532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 14th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04789871","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005673302","display_name":"Seanghort Born","orcid":"https://orcid.org/0000-0003-0859-4627"},"institutions":[{"id":"https://openalex.org/I186365177","display_name":"Institute of Technology of Cambodia","ror":"https://ror.org/054z67s11","country_code":"KH","type":"education","lineage":["https://openalex.org/I186365177"]}],"countries":["KH"],"is_corresponding":true,"raw_author_name":"Seanghort Born","raw_affiliation_strings":["Institute of Technology of Cambodia,Department of Information and Communication Engineering,Cambodia","Department of Information and Communication Engineering, Institute of Technology of Cambodia, Cambodia"],"affiliations":[{"raw_affiliation_string":"Institute of Technology of Cambodia,Department of Information and Communication Engineering,Cambodia","institution_ids":["https://openalex.org/I186365177"]},{"raw_affiliation_string":"Department of Information and Communication Engineering, Institute of Technology of Cambodia, Cambodia","institution_ids":["https://openalex.org/I186365177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033389188","display_name":"Dona Valy","orcid":"https://orcid.org/0009-0000-6181-5551"},"institutions":[{"id":"https://openalex.org/I186365177","display_name":"Institute of Technology of Cambodia","ror":"https://ror.org/054z67s11","country_code":"KH","type":"education","lineage":["https://openalex.org/I186365177"]}],"countries":["KH"],"is_corresponding":false,"raw_author_name":"Dona Valy","raw_affiliation_strings":["Institute of Technology of Cambodia,Department of Information and Communication Engineering,Cambodia","Department of Information and Communication Engineering, Institute of Technology of Cambodia, Cambodia"],"affiliations":[{"raw_affiliation_string":"Institute of Technology of Cambodia,Department of Information and Communication Engineering,Cambodia","institution_ids":["https://openalex.org/I186365177"]},{"raw_affiliation_string":"Department of Information and Communication Engineering, Institute of Technology of Cambodia, Cambodia","institution_ids":["https://openalex.org/I186365177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033004243","display_name":"Phutphalla Kong","orcid":"https://orcid.org/0000-0003-1659-6745"},"institutions":[{"id":"https://openalex.org/I186365177","display_name":"Institute of Technology of Cambodia","ror":"https://ror.org/054z67s11","country_code":"KH","type":"education","lineage":["https://openalex.org/I186365177"]}],"countries":["KH"],"is_corresponding":false,"raw_author_name":"Phutphalla Kong","raw_affiliation_strings":["Institute of Technology of Cambodia,Department of Information and Communication Engineering,Cambodia","Department of Information and Communication Engineering, Institute of Technology of Cambodia, Cambodia"],"affiliations":[{"raw_affiliation_string":"Institute of Technology of Cambodia,Department of Information and Communication Engineering,Cambodia","institution_ids":["https://openalex.org/I186365177"]},{"raw_affiliation_string":"Department of Information and Communication Engineering, Institute of Technology of Cambodia, Cambodia","institution_ids":["https://openalex.org/I186365177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005673302"],"corresponding_institution_ids":["https://openalex.org/I186365177"],"apc_list":null,"apc_paid":null,"fwci":0.2013,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49959932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"234","last_page":"238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9947999715805054,"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":0.9491000175476074,"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":0.8679929971694946},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6569458842277527},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6407592296600342},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6169986724853516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6060813665390015},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5870299339294434},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.574681282043457},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5649349689483643},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.553286075592041},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5236475467681885},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.516883373260498},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45900958776474},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16271960735321045},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11248329281806946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8679929971694946},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6569458842277527},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6407592296600342},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6169986724853516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6060813665390015},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5870299339294434},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.574681282043457},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5649349689483643},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.553286075592041},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5236475467681885},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.516883373260498},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45900958776474},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16271960735321045},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11248329281806946},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/skima57145.2022.10029532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/skima57145.2022.10029532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 14th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04789871v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04789871","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2022 14th International Conference on Software, Knowledge, Information Management and Applications (SKIMA), Dec 2022, Phnom Penh, Cambodia. pp.234 - 238, &#x27E8;10.1109/skima57145.2022.10029532&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04789871v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04789871","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2022 14th International Conference on Software, Knowledge, Information Management and Applications (SKIMA), Dec 2022, Phnom Penh, Cambodia. pp.234 - 238, &#x27E8;10.1109/skima57145.2022.10029532&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2120770606","https://openalex.org/W2414582505","https://openalex.org/W2759181158","https://openalex.org/W2781760569","https://openalex.org/W2900353077","https://openalex.org/W2905440625","https://openalex.org/W2963026768","https://openalex.org/W2964325005","https://openalex.org/W3107623930","https://openalex.org/W3141961557","https://openalex.org/W3157745755","https://openalex.org/W4205647326","https://openalex.org/W6631190155","https://openalex.org/W6678233655","https://openalex.org/W7052950706"],"related_works":["https://openalex.org/W2161008081","https://openalex.org/W2100947578","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W1974418053","https://openalex.org/W2081317458","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Correcting":[0],"spelling":[1],"errors":[2],"in":[3,26],"texts":[4],"extracted":[5,116],"from":[6,117],"Khmer":[7,22,114],"palm":[8],"leaf":[9],"manuscripts":[10],"by":[11],"handwritten":[12],"text":[13,51,110],"recognition":[14,52],"(HTR)":[15],"systems":[16],"can":[17],"be":[18],"very":[19],"challenging.":[20],"A":[21],"Language":[23],"Model":[24],"developed":[25],"this":[27],"study":[28],"aims":[29],"to":[30,55,83,95],"facilitate":[31],"the":[32,48,66,85,88,99],"task":[33],"mentioned":[34],"above.":[35],"The":[36,63],"proposed":[37],"model":[38,68],"utilizes":[39],"long":[40],"short-term":[41],"memory":[42],"(LSTM)":[43],"modules":[44],"applicable":[45],"for":[46],"improving":[47],"performance":[49],"of":[50,59,65,78,87,113],"which":[53,75],"is":[54,69,76],"predict":[56,98],"a":[57,93,109],"sequence":[58],"characters":[60],"as":[61],"output.":[62],"architecture":[64],"language":[67],"based":[70],"on":[71,108],"an":[72,81],"encoder-decoder":[73],"mechanism":[74],"composed":[77],"two":[79],"parts:":[80],"encoder":[82],"capture":[84],"context":[86],"input":[89],"erroneous":[90],"word":[91],"and":[92,97],"decoder":[94],"decode":[96],"correctly":[100],"spelt":[101],"output":[102],"word.":[103],"Experimental":[104],"evaluations":[105],"are":[106],"conducted":[107],"corpus":[111],"consisting":[112],"words":[115],"Sleuk-Rith":[118],"set.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
