{"id":"https://openalex.org/W4417029431","doi":"https://doi.org/10.1007/s00799-025-00437-5","title":"STRAS: a semantic textual-cues leveraged Rule-based approach for article separation in historical newspapers","display_name":"STRAS: a semantic textual-cues leveraged Rule-based approach for article separation in historical newspapers","publication_year":2025,"publication_date":"2025-12-05","ids":{"openalex":"https://openalex.org/W4417029431","doi":"https://doi.org/10.1007/s00799-025-00437-5"},"language":"en","primary_location":{"id":"doi:10.1007/s00799-025-00437-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00799-025-00437-5","pdf_url":null,"source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","raw_type":"journal-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/A5088364254","display_name":"Nancy Girdhar","orcid":"https://orcid.org/0000-0002-1009-3875"},"institutions":[{"id":"https://openalex.org/I897542642","display_name":"University of Plymouth","ror":"https://ror.org/008n7pv89","country_code":"GB","type":"education","lineage":["https://openalex.org/I897542642"]},{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR","GB"],"is_corresponding":true,"raw_author_name":"Nancy Girdhar","raw_affiliation_strings":["L3i, University of La Rochelle, La Rochelle, 17000, France","School of Engineering, Computing and Mathematics, University of Plymouth, Plymouth, PL4 8AA, UK"],"affiliations":[{"raw_affiliation_string":"L3i, University of La Rochelle, La Rochelle, 17000, France","institution_ids":["https://openalex.org/I78744979"]},{"raw_affiliation_string":"School of Engineering, Computing and Mathematics, University of Plymouth, Plymouth, PL4 8AA, UK","institution_ids":["https://openalex.org/I897542642"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063992777","display_name":"Micka\u00ebl Coustaty","orcid":"https://orcid.org/0000-0002-0123-439X"},"institutions":[{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Micka\u00ebl Coustaty","raw_affiliation_strings":["L3i, University of La Rochelle, La Rochelle, 17000, France"],"affiliations":[{"raw_affiliation_string":"L3i, University of La Rochelle, La Rochelle, 17000, France","institution_ids":["https://openalex.org/I78744979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033491986","display_name":"Antoine Doucet","orcid":"https://orcid.org/0000-0001-6160-3356"},"institutions":[{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Doucet","raw_affiliation_strings":["L3i, University of La Rochelle, La Rochelle, 17000, France"],"affiliations":[{"raw_affiliation_string":"L3i, University of La Rochelle, La Rochelle, 17000, France","institution_ids":["https://openalex.org/I78744979"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088364254"],"corresponding_institution_ids":["https://openalex.org/I78744979","https://openalex.org/I897542642"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41373241,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.6211000084877014,"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":0.6211000084877014,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1005999967455864,"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/T10028","display_name":"Topic Modeling","score":0.05130000039935112,"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/newspaper","display_name":"Newspaper","score":0.7419999837875366},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.7414000034332275},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5848000049591064},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5315999984741211},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4706000089645386},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4154999852180481},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.40059998631477356},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3619000017642975}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8331999778747559},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.7419999837875366},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.7414000034332275},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.612500011920929},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5848000049591064},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5315999984741211},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4706000089645386},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37700000405311584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36390000581741333},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3102000057697296},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.2881999909877777},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2687999904155731},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2632000148296356},{"id":"https://openalex.org/C173862523","wikidata":"https://www.wikidata.org/wiki/Q5421270","display_name":"Explicit semantic analysis","level":5,"score":0.2614000141620636},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00799-025-00437-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00799-025-00437-5","pdf_url":null,"source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1992181154","https://openalex.org/W1998729616","https://openalex.org/W2001968227","https://openalex.org/W2052301383","https://openalex.org/W2089298206","https://openalex.org/W2090985514","https://openalex.org/W2131448412","https://openalex.org/W2132886386","https://openalex.org/W2133003941","https://openalex.org/W2154032543","https://openalex.org/W2250473257","https://openalex.org/W2493916176","https://openalex.org/W2618530766","https://openalex.org/W2963626623","https://openalex.org/W2963918774","https://openalex.org/W2964346820","https://openalex.org/W2970641574","https://openalex.org/W2981788981","https://openalex.org/W3003867532","https://openalex.org/W3006661061","https://openalex.org/W3163273160","https://openalex.org/W4220926422","https://openalex.org/W4241588219","https://openalex.org/W4282597027","https://openalex.org/W4327644051","https://openalex.org/W4389150549","https://openalex.org/W4393627823","https://openalex.org/W4393714034","https://openalex.org/W4394698875","https://openalex.org/W4402384622"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-12-05T23:25:22.460635","created_date":"2025-12-05T00:00:00"}