{"id":"https://openalex.org/W2132368650","doi":"https://doi.org/10.1109/icdar.2003.1227778","title":"Using tree-grammars for training set expansion in page classi .cation","display_name":"Using tree-grammars for training set expansion in page classi .cation","publication_year":2005,"publication_date":"2005-04-12","ids":{"openalex":"https://openalex.org/W2132368650","doi":"https://doi.org/10.1109/icdar.2003.1227778","mag":"2132368650"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2003.1227778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2003.1227778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","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/A5011544731","display_name":"Simone Baldi","orcid":"https://orcid.org/0000-0002-5151-2618"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"S. Baldi","raw_affiliation_strings":["DSI-University of Florence, Italy","DSI, University of Florence"],"affiliations":[{"raw_affiliation_string":"DSI-University of Florence, Italy","institution_ids":["https://openalex.org/I45084792"]},{"raw_affiliation_string":"DSI, University of Florence","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011511343","display_name":"Simone Marinai","orcid":"https://orcid.org/0000-0002-6702-2277"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"S. Marinai","raw_affiliation_strings":["DSI-University of Florence, Italy","DSI - University of Florence, Italy"],"affiliations":[{"raw_affiliation_string":"DSI-University of Florence, Italy","institution_ids":["https://openalex.org/I45084792"]},{"raw_affiliation_string":"DSI - University of Florence, Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072297116","display_name":"G. Soda","orcid":"https://orcid.org/0000-0003-1807-1539"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"G. Soda","raw_affiliation_strings":["DSI-University of Florence, Italy","DSI - University of Florence, Italy"],"affiliations":[{"raw_affiliation_string":"DSI-University of Florence, Italy","institution_ids":["https://openalex.org/I45084792"]},{"raw_affiliation_string":"DSI - University of Florence, Italy","institution_ids":["https://openalex.org/I45084792"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011544731"],"corresponding_institution_ids":["https://openalex.org/I45084792"],"apc_list":null,"apc_paid":null,"fwci":1.175,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.81303368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"829","last_page":"833"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9958999752998352,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9958999752998352,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9952999949455261,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9948999881744385,"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":0.7575442790985107},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.582707405090332},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5046170949935913},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4743722081184387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4560137391090393},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3967132568359375},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14272230863571167},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10959506034851074},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06400632858276367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7575442790985107},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.582707405090332},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5046170949935913},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4743722081184387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4560137391090393},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3967132568359375},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14272230863571167},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10959506034851074},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06400632858276367}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdar.2003.1227778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2003.1227778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1976373002","https://openalex.org/W2016868026","https://openalex.org/W2120259239","https://openalex.org/W2125318232","https://openalex.org/W2128649316","https://openalex.org/W2130746998","https://openalex.org/W6679305017"],"related_works":["https://openalex.org/W623847618","https://openalex.org/W2131848667","https://openalex.org/W2065974963","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W1526908682","https://openalex.org/W2020595170","https://openalex.org/W2951359407","https://openalex.org/W3192589309"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"describe":[4],"a":[5,69],"method":[6],"for":[7],"the":[8,35,42,44,62,74],"expansionof":[9],"training":[10,63],"sets":[11],"made":[12],"by":[13,49],"XY":[14],"trees":[15],"representing":[16],"page":[17,25,30],"layout.This":[18],"approach":[19],"is":[20,34,78],"appropriate":[21],"when":[22],"dealing":[23],"with":[24,68],"classificationbased":[26],"on":[27],"MXY":[28],"tree":[29,38,45],"representations.":[31],"The":[32],"basicidea":[33],"use":[36],"of":[37,53,81],"grammars":[39],"to":[40],"model":[41],"variationsin":[43],"which":[46],"are":[47,57,66],"caused":[48],"segmentation":[50],"algorithms.A":[51],"set":[52],"general":[54],"grammatical":[55],"rules":[56],"defined":[58],"and":[59],"used":[60],"toexpand":[61],"set.":[64],"Pages":[65],"classified":[67],"k":[70],"-":[71],"nnapproach":[72],"where":[73],"distance":[75],"between":[76],"pages":[77],"computed":[79],"bymeans":[80],"tree-edit":[82],"distance.":[83]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}