{"id":"https://openalex.org/W7155636456","doi":"https://doi.org/10.1145/3789418.3789430","title":"Transformer-based Text Segmentation for Indonesian: Benchmarking and Application to Abstractive Summarization","display_name":"Transformer-based Text Segmentation for Indonesian: Benchmarking and Application to Abstractive Summarization","publication_year":2025,"publication_date":"2025-12-12","ids":{"openalex":"https://openalex.org/W7155636456","doi":"https://doi.org/10.1145/3789418.3789430"},"language":null,"primary_location":{"id":"doi:10.1145/3789418.3789430","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3789418.3789430","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Conference on Algorithms, Computing and Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3789418.3789430","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071033295","display_name":"Valentinus Roby Hananto","orcid":"https://orcid.org/0000-0003-1988-3168"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Valentinus R. Hananto","raw_affiliation_strings":["College of Information Science and Engineering, Ritsumeikan University, Osaka, Japan,"],"raw_orcid":"https://orcid.org/0000-0003-1988-3168","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ritsumeikan University, Osaka, Japan,","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093936494","display_name":"Michael Evan Santoso","orcid":"https://orcid.org/0000-0002-5002-0275"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Michael E. Santoso","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Ritsumeikan University, Osaka, Japan,"],"raw_orcid":"https://orcid.org/0000-0002-5002-0275","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Ritsumeikan University, Osaka, Japan,","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087315620","display_name":"Vivine Nurcahyawati","orcid":"https://orcid.org/0000-0002-6611-9974"},"institutions":[{"id":"https://openalex.org/I4210146942","display_name":"Universitas Widya Kartika","ror":"https://ror.org/04t27vc74","country_code":"ID","type":"education","lineage":["https://openalex.org/I4210146942"]},{"id":"https://openalex.org/I4210158289","display_name":"Universitas 45 Surabaya","ror":"https://ror.org/04xmkh626","country_code":"ID","type":"education","lineage":["https://openalex.org/I4210158289"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Vivine Nurcahyawati","raw_affiliation_strings":["Department of Information Systems, Universitas Dinamika, Surabaya, Indonesia,"],"raw_orcid":"https://orcid.org/0000-0002-6611-9974","affiliations":[{"raw_affiliation_string":"Department of Information Systems, Universitas Dinamika, Surabaya, Indonesia,","institution_ids":["https://openalex.org/I4210146942","https://openalex.org/I4210158289"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84163796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"92","last_page":"98"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8813999891281128,"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":0.8813999891281128,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.03280000016093254,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.017000000923871994,"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":0.8226000070571899},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.8075000047683716},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7351999878883362},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6481999754905701},{"id":"https://openalex.org/keywords/indonesian","display_name":"Indonesian","score":0.3531000018119812},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.3278000056743622},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3206999897956848}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8226000070571899},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8075000047683716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7840999960899353},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7351999878883362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6704999804496765},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6481999754905701},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5810999870300293},{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.3278000056743622},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30559998750686646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30329999327659607},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2962000072002411},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.26100000739097595}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3789418.3789430","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3789418.3789430","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Conference on Algorithms, Computing and Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3789418.3789430","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3789418.3789430","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Conference on Algorithms, Computing and Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6863689422607422,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1557074680","https://openalex.org/W2159083595","https://openalex.org/W2303837218","https://openalex.org/W2512217112","https://openalex.org/W2807938752","https://openalex.org/W2962716111","https://openalex.org/W2963341956","https://openalex.org/W2989200142","https://openalex.org/W3014723908","https://openalex.org/W3116407756","https://openalex.org/W3205577628","https://openalex.org/W4221110890","https://openalex.org/W4221142221","https://openalex.org/W4225934689","https://openalex.org/W4385567296","https://openalex.org/W4385571140","https://openalex.org/W4388996790"],"related_works":[],"abstract_inverted_index":{"This":[0,42],"study":[1,30,68],"benchmarks":[2],"transformer-based,":[3],"topic-modeling,":[4],"and":[5,52,63],"classical":[6],"methods":[7],"for":[8,48,56],"text":[9,50],"segmentation":[10,26,37,51],"in":[11,25,66],"Indonesian.":[12],"Experiments":[13],"on":[14,31,72],"the":[15,45],"Indonesian":[16,49],"Wikipedia":[17],"dataset":[18],"demonstrate":[19],"that":[20,35],"transformer-based":[21],"embeddings":[22],"outperform":[23],"baselines":[24],"accuracy.":[27],"A":[28],"case":[29],"abstractive":[32],"summarization":[33],"demonstrates":[34],"coherent":[36],"improves":[38],"human-judged":[39],"summary":[40],"quality.":[41],"work":[43],"establishes":[44],"first":[46],"benchmark":[47],"highlights":[53],"its":[54],"benefits":[55],"downstream":[57],"NLP":[58],"tasks.":[59],"The":[60],"source":[61],"code":[62],"datasets":[64],"used":[65],"this":[67],"are":[69],"publicly":[70],"available":[71],"https://github.com/blacfli/indo_text_segmentation":[73]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-26T00:00:00"}