{"id":"https://openalex.org/W7140075415","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.278","title":"Leveraging Digitized Newspapers to Collect Summarization Data in Low-Resource Languages","display_name":"Leveraging Digitized Newspapers to Collect Summarization Data in Low-Resource Languages","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140075415","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.278"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.278","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.278","pdf_url":"https://aclanthology.org/2026.findings-eacl.278.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.278.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114655779","display_name":"Noam Dahan","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Noam Dahan","raw_affiliation_strings":["The Hebrew University of Jerusalem"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hebrew University of Jerusalem","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130390144","display_name":"Omer Kidron","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Omer Kidron","raw_affiliation_strings":["The Hebrew University of Jerusalem"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hebrew University of Jerusalem","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130351726","display_name":"Gabriel Stanovsky","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gabriel Stanovsky","raw_affiliation_strings":["The Hebrew University of Jerusalem"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hebrew University of Jerusalem","institution_ids":["https://openalex.org/I197251160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197251160"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5260","last_page":"5273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2865000069141388,"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/T10028","display_name":"Topic Modeling","score":0.2865000069141388,"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/T11719","display_name":"Data Quality and Management","score":0.1590999960899353,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.06589999794960022,"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/automatic-summarization","display_name":"Automatic summarization","score":0.7325999736785889},{"id":"https://openalex.org/keywords/newspaper","display_name":"Newspaper","score":0.6079999804496765},{"id":"https://openalex.org/keywords/headline","display_name":"Headline","score":0.30230000615119934},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2775999903678894}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7325999736785889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7264000177383423},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.6079999804496765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4269999861717224},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3871999979019165},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38659998774528503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.367900013923645},{"id":"https://openalex.org/C2778689934","wikidata":"https://www.wikidata.org/wiki/Q1313396","display_name":"Headline","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.278","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.278","pdf_url":"https://aclanthology.org/2026.findings-eacl.278.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.278","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.278","pdf_url":"https://aclanthology.org/2026.findings-eacl.278.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.43106600642204285}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140075415.pdf","grobid_xml":"https://content.openalex.org/works/W7140075415.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"High":[0],"quality":[1],"summarization":[2,90],"data":[3,62],"remains":[4],"scarce":[5],"in":[6,92],"under-represented":[7],"languages.However,":[8],"historical":[9],"newspapers,":[10],"made":[11],"available":[12],"through":[13],"recent":[14],"digitization":[15],"efforts,":[16],"offer":[17],"an":[18,66],"abundant":[19],"source":[20],"of":[21],"untapped,":[22],"naturally":[23,35],"annotated":[24],"data.In":[25],"this":[26,49,77],"work,":[27],"we":[28,64,75],"present":[29],"a":[30,80],"novel":[31],"method":[32],"for":[33],"collecting":[34],"occurring":[36],"summaries":[37],"via":[38],"Front-Page":[39],"Teasers,":[40],"where":[41],"editors":[42],"summarize":[43],"full":[44],"length":[45],"articles.We":[46],"show":[47],"that":[48],"phenomenon":[50],"is":[51],"common":[52],"across":[53],"seven":[54],"diverse":[55],"languages":[56],"and":[57],"supports":[58],"multi-document":[59],"summarization.To":[60],"scale":[61],"collection,":[63],"develop":[65],"automatic":[67],"process,":[68],"suited":[69],"to":[70,79],"varying":[71],"linguistic":[72],"resource":[73],"levels.Finally,":[74],"apply":[76],"process":[78],"Hebrew":[81,93],"newspaper":[82],"title,":[83],"producing":[84],"HEBTEASESUM,":[85],"the":[86],"first":[87],"dedicated":[88],"multidocument":[89],"dataset":[91],"1":[94],".":[95]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-24T00:00:00"}
