{"id":"https://openalex.org/W4416035708","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1351","title":"Exploring Quality and Diversity in Synthetic Data Generation for Argument Mining","display_name":"Exploring Quality and Diversity in Synthetic Data Generation for Argument Mining","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035708","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1351"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1351","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1351","pdf_url":"https://aclanthology.org/2025.emnlp-main.1351.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1351.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020779586","display_name":"Jianzhu Bao","orcid":"https://orcid.org/0009-0004-9818-8765"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jianzhu Bao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101708681","display_name":"Yuqi Huang","orcid":"https://orcid.org/0009-0006-6737-2572"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuqi Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115597021","display_name":"Yang Sun","orcid":"https://orcid.org/0009-0004-9501-3599"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Sun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101936536","display_name":"Wenya Wang","orcid":"https://orcid.org/0000-0003-2624-5498"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenya Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100310357","display_name":"Yice Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yice Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109789552","display_name":"Bojun Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bojun Jin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026719663","display_name":"Ruifeng Xu","orcid":"https://orcid.org/0000-0002-4009-5679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruifeng Xu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5020779586"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1720239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26592","last_page":"26615"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.27950000762939453,"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":0.27950000762939453,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.15950000286102295,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.10450000315904617,"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/quality","display_name":"Quality (philosophy)","score":0.5705999732017517},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.5292999744415283},{"id":"https://openalex.org/keywords/argument","display_name":"Argument (complex analysis)","score":0.48980000615119934},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.475600004196167},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.45809999108314514},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.3021000027656555}],"concepts":[{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5705999732017517},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.5292999744415283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5065000057220459},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.45809999108314514},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39340001344680786},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36340001225471497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3463999927043915},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.28619998693466187},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1351","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1351","pdf_url":"https://aclanthology.org/2025.emnlp-main.1351.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1351","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1351","pdf_url":"https://aclanthology.org/2025.emnlp-main.1351.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2230680632","display_name":null,"funder_award_id":"PCL2023A09","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G37568934","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6312846351","display_name":null,"funder_award_id":"62176076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8955107213","display_name":null,"funder_award_id":"Major","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035708.pdf","grobid_xml":"https://content.openalex.org/works/W4416035708.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"advancement":[1],"of":[2,14,103,126],"Argument":[3],"Mining":[4],"(AM)":[5],"is":[6],"hindered":[7],"by":[8,23],"a":[9,51,64],"critical":[10],"bottleneck:":[11],"the":[12,101,113,124],"scarcity":[13],"structure-annotated":[15],"datasets,":[16],"which":[17,55,68],"are":[18],"expensive":[19],"to":[20,40,59],"create":[21],"manually.Inspired":[22],"recent":[24],"successes":[25],"in":[26,108],"synthetic":[27,42,90,117],"data":[28,43,87,118],"generation":[29],"across":[30],"various":[31],"NLP":[32],"tasks,":[33],"this":[34],"paper":[35],"explores":[36],"methodologies":[37],"for":[38,44],"LLMs":[39],"generate":[41],"AM.We":[45],"investigate":[46],"two":[47],"complementary":[48],"synthesis":[49,53,66],"perspectives:":[50],"quality-oriented":[52],"approach,":[54,67],"employs":[56],"structure-aware":[57],"paraphrasing":[58],"preserve":[60],"annotation":[61],"quality,":[62],"and":[63,76,110,120],"diversity-oriented":[65,97],"generates":[69],"novel":[70],"argumentative":[71],"texts":[72],"with":[73,88],"diverse":[74],"topics":[75],"argument":[77],"structures.Experiments":[78],"on":[79],"three":[80],"datasets":[81],"show":[82],"that":[83],"augmenting":[84],"original":[85],"training":[86],"our":[89,127],"data,":[91],"particularly":[92],"when":[93],"combining":[94],"both":[95,107],"quality-and":[96],"instances,":[98],"significantly":[99],"enhances":[100],"performance":[102,122],"existing":[104],"AM":[105],"models,":[106],"full-data":[109],"low-resource":[111],"settings.Moreover,":[112],"positive":[114],"correlation":[115],"between":[116],"volume":[119],"model":[121],"highlights":[123],"scalability":[125],"methods.":[128]},"counts_by_year":[],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-11-08T00:00:00"}