{"id":"https://openalex.org/W2037378121","doi":"https://doi.org/10.1109/isccsp.2012.6217760","title":"A novel segmentation technique for splitting a typed Persian text to sub-words","display_name":"A novel segmentation technique for splitting a typed Persian text to sub-words","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W2037378121","doi":"https://doi.org/10.1109/isccsp.2012.6217760","mag":"2037378121"},"language":"en","primary_location":{"id":"doi:10.1109/isccsp.2012.6217760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isccsp.2012.6217760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 5th International Symposium on Communications, Control and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011245170","display_name":"Mahnaz Shafii","orcid":null},"institutions":[{"id":"https://openalex.org/I74413500","display_name":"University of Windsor","ror":"https://ror.org/01gw3d370","country_code":"CA","type":"education","lineage":["https://openalex.org/I74413500"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Mahnaz Shafii","raw_affiliation_strings":["University of Windsor, ONT, Canada","University of Windsor, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Windsor, ONT, Canada","institution_ids":["https://openalex.org/I74413500"]},{"raw_affiliation_string":"University of Windsor, ON, Canada","institution_ids":["https://openalex.org/I74413500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035291753","display_name":"M.A. Sid-Ahmed","orcid":null},"institutions":[{"id":"https://openalex.org/I74413500","display_name":"University of Windsor","ror":"https://ror.org/01gw3d370","country_code":"CA","type":"education","lineage":["https://openalex.org/I74413500"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Maher A. Sid-Ahmed","raw_affiliation_strings":["University of Windsor, ONT, Canada","University of Windsor, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Windsor, ONT, Canada","institution_ids":["https://openalex.org/I74413500"]},{"raw_affiliation_string":"University of Windsor, ON, Canada","institution_ids":["https://openalex.org/I74413500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5116239815","display_name":"Majid Ahmadi","orcid":"https://orcid.org/0009-0006-4046-2121"},"institutions":[{"id":"https://openalex.org/I74413500","display_name":"University of Windsor","ror":"https://ror.org/01gw3d370","country_code":"CA","type":"education","lineage":["https://openalex.org/I74413500"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Majid Ahmadi","raw_affiliation_strings":["University of Windsor, ONT, Canada","University of Windsor, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Windsor, ONT, Canada","institution_ids":["https://openalex.org/I74413500"]},{"raw_affiliation_string":"University of Windsor, ON, Canada","institution_ids":["https://openalex.org/I74413500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011245170"],"corresponding_institution_ids":["https://openalex.org/I74413500"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.11009546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9944999814033508,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/persian","display_name":"Persian","score":0.9380879402160645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6824859380722046},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6595892906188965},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6247309446334839},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.6177310943603516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5998178124427795},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5992485880851746},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4827977418899536},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.43097764253616333},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.4242191016674042},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39088448882102966},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23606032133102417},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17517951130867004},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09006685018539429}],"concepts":[{"id":"https://openalex.org/C2776527531","wikidata":"https://www.wikidata.org/wiki/Q9168","display_name":"Persian","level":2,"score":0.9380879402160645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6824859380722046},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6595892906188965},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6247309446334839},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6177310943603516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5998178124427795},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5992485880851746},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4827977418899536},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.43097764253616333},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.4242191016674042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39088448882102966},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23606032133102417},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17517951130867004},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09006685018539429},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isccsp.2012.6217760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isccsp.2012.6217760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 5th International Symposium on Communications, Control and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1721747439","https://openalex.org/W1977582554","https://openalex.org/W2004127884","https://openalex.org/W2017787659","https://openalex.org/W2127975771","https://openalex.org/W2155332378","https://openalex.org/W2185932075","https://openalex.org/W2338499345","https://openalex.org/W3023411394","https://openalex.org/W4285719527","https://openalex.org/W6637463702","https://openalex.org/W6687141766"],"related_works":["https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2393940967","https://openalex.org/W2159591557","https://openalex.org/W2785359773","https://openalex.org/W2058548953","https://openalex.org/W2385598138","https://openalex.org/W2366925922"],"abstract_inverted_index":{"One":[0],"common":[1],"approach":[2,32],"in":[3],"recognition":[4],"of":[5,28,67],"a":[6,51,64,74,80,88],"Persian":[7,29,43,52,81],"text":[8,13,53,82],"is":[9,33],"to":[10,21,25,55,78,83],"segment":[11,50],"the":[12,93],"into":[14],"its":[15,56,84],"component":[16,57],"words":[17,20],"and":[18,35,59,95],"then":[19],"single":[22],"characters.":[23],"Due":[24],"specific":[26],"characteristics":[27],"words,":[30],"this":[31,70],"non-trivial":[34],"literature":[36],"reports":[37],"relatively":[38],"low":[39],"success":[40,90],"rate":[41,91],"for":[42,92],"character":[44],"segmentation.":[45],"As":[46],"an":[47],"alternative,":[48],"we":[49,72],"only":[54],"sub-words;":[58],"then,":[60],"recognize":[61],"sub-words":[62,85],"from":[63],"large":[65],"library":[66],"sub-words.":[68],"In":[69],"document,":[71],"describe":[73],"novel":[75],"segmentation":[76],"technique":[77],"split":[79],"components":[86],"with":[87],"perfect":[89],"texts":[94],"fonts":[96],"tested.":[97]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}