{"id":"https://openalex.org/W4404782680","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.109","title":"An Effective Deployment of Diffusion LM for Data Augmentation in Low-Resource Sentiment Classification","display_name":"An Effective Deployment of Diffusion LM for Data Augmentation in Low-Resource Sentiment Classification","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404782680","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.109"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.emnlp-main.109","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.109","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.109","pdf_url":"https://aclanthology.org/2024.emnlp-main.109.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2024.emnlp-main.109.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056344041","display_name":"Zhuowei Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuowei Chen","raw_affiliation_strings":["Guangdong University of Foreign Studies , Guangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Foreign Studies , Guangzhou , China","institution_ids":["https://openalex.org/I186272606"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022448274","display_name":"Lianxi Wang","orcid":"https://orcid.org/0000-0002-6746-6476","observed_orcids":["https://orcid.org/0000-0002-6746-6476"]},"institutions":[{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianxi Wang","raw_affiliation_strings":["Guangdong University of Foreign Studies , Guangzhou , China","Guangzhou Key Laboratory of Multilingual Intelligent Processing , Guangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Foreign Studies , Guangzhou , China","institution_ids":["https://openalex.org/I186272606"]},{"raw_affiliation_string":"Guangzhou Key Laboratory of Multilingual Intelligent Processing , Guangzhou , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102737709","display_name":"Yiwen Wu","orcid":"https://orcid.org/0000-0003-0241-7988","observed_orcids":["https://orcid.org/0000-0003-0241-7988"]},"institutions":[{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuben Wu","raw_affiliation_strings":["Guangdong University of Foreign Studies , Guangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Foreign Studies , Guangzhou , China","institution_ids":["https://openalex.org/I186272606"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinfeng Liao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinfeng Liao","raw_affiliation_strings":["Guangdong University of Foreign Studies , Guangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Foreign Studies , Guangzhou , China","institution_ids":["https://openalex.org/I186272606"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101619013","display_name":"Yujia Tian","orcid":"https://orcid.org/0009-0009-6982-727X","observed_orcids":["https://orcid.org/0009-0009-6982-727X"]},"institutions":[{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujia Tian","raw_affiliation_strings":["Guangdong University of Foreign Studies , Guangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Foreign Studies , Guangzhou , China","institution_ids":["https://openalex.org/I186272606"]}]},{"author_position":"last","author":{"id":null,"display_name":"Junyang Zhong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyang Zhong","raw_affiliation_strings":["Guangdong University of Foreign Studies , Guangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong University of Foreign Studies , Guangzhou , China","institution_ids":["https://openalex.org/I186272606"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I186272606"],"apc_list":null,"apc_paid":null,"fwci":1.2629,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84719507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1844","last_page":"1856"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9980000257492065,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9980000257492065,"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/T10028","display_name":"Topic Modeling","score":0.0013000000035390258,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":9.999999747378752e-05,"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/sentiment-classification","display_name":"sentiment classification","score":0.8849999904632568},{"id":"https://openalex.org/keywords/low-resource-learning","display_name":"low-resource learning","score":0.6510000228881836},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.6880000233650208},{"id":"https://openalex.org/keywords/diffusion-language-models","display_name":"diffusion language models","score":0.9610000252723694},{"id":"https://openalex.org/keywords/pseudo-labeling","display_name":"pseudo-labeling","score":0.8270000219345093},{"id":"https://openalex.org/keywords/domain-specific-sentiment","display_name":"domain-specific sentiment","score":0.7239999771118164},{"id":"https://openalex.org/keywords/few-shot-learning","display_name":"few-shot learning","score":0.7170000076293945}],"concepts":[{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.8244293928146362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995144486427307},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6697196960449219},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5568950176239014},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3368186950683594},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.06854936480522156},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06607404351234436},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.064766526222229},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2024.emnlp-main.109","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.109","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.109","pdf_url":"https://aclanthology.org/2024.emnlp-main.109.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.03203","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.03203","pdf_url":"https://arxiv.org/pdf/2409.03203","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.03203","doi":"https://doi.org/10.48550/arxiv.2409.03203","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.03203","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.emnlp-main.109","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.109","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.109","pdf_url":"https://aclanthology.org/2024.emnlp-main.109.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327557","display_name":"National Office for Philosophy and Social Sciences","ror":"https://ror.org/04m0ms912"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404782680.pdf","grobid_xml":"https://content.openalex.org/works/W4404782680.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2765407302","https://openalex.org/W2896457183","https://openalex.org/W2922917409","https://openalex.org/W2965373594","https://openalex.org/W2975059944","https://openalex.org/W4287755489","https://openalex.org/W4309590843","https://openalex.org/W4386876215"],"related_works":["https://openalex.org/W4413237117","https://openalex.org/W7160118308","https://openalex.org/W4385570440","https://openalex.org/W7127630331","https://openalex.org/W7131792808","https://openalex.org/W4412152623","https://openalex.org/W4386694317","https://openalex.org/W4392088226","https://openalex.org/W4409820859","https://openalex.org/W4407129259"],"abstract_inverted_index":{"Sentiment":[0],"classification":[1],"(SC)":[2],"often":[3],"suffers":[4],"from":[5],"low-resource":[6,147],"challenges":[7],"such":[8],"as":[9],"domainspecific":[10],"contexts,":[11],"imbalanced":[12],"label":[13],"distributions,":[14],"and":[15,41,100,115,122,151,162],"few-shot":[16],"scenarios.The":[17],"potential":[18],"of":[19,43,67,78,120,126,142,158],"the":[20,39,58,62,65,76,79,118,136,140,156],"diffusion":[21,94],"language":[22,63],"model":[23,137],"(LM)":[24],"for":[25],"textual":[26,33],"data":[27],"augmentation":[28],"(DA)":[29],"remains":[30],"unexplored,":[31],"moreover,":[32],"DA":[34,46],"methods":[35,47],"struggle":[36],"to":[37,83,91,96,134],"balance":[38,112],"diversity":[40],"consistency":[42,114],"new":[44],"samples.Most":[45],"either":[48],"perform":[49],"logical":[50],"modifications":[51],"or":[52],"rephrase":[53],"less":[54,85],"important":[55,86],"tokens":[56,71],"in":[57,145],"original":[59],"sequence":[60],"with":[61],"model.In":[64],"context":[66],"SC,":[68],"strong":[69,106],"emotional":[70],"could":[72],"act":[73],"critically":[74],"on":[75],"sentiment":[77],"whole":[80],"sequence.Therefore,":[81],"contrary":[82],"rephrasing":[84],"context,":[87],"we":[88],"propose":[89],"DiffusionCLS":[90],"leverage":[92],"a":[93,111,130],"LM":[95],"capture":[97],"in-domain":[98],"knowledge":[99],"generate":[101],"pseudo":[102],"samples":[103],"by":[104],"reconstructing":[105],"label-related":[107],"tokens.This":[108],"approach":[109],"ensures":[110],"between":[113],"diversity,":[116],"avoiding":[117],"introduction":[119],"noise":[121],"augmenting":[123],"crucial":[124],"features":[125],"datasets.Dif-fusionCLS":[127],"also":[128],"comprises":[129],"Noise-Resistant":[131],"Training":[132],"objective":[133],"help":[135],"generalize.Experiments":[138],"demonstrate":[139],"effectiveness":[141,157],"our":[143,159,170],"method":[144],"various":[146],"scenarios":[148],"including":[149],"domain-specific":[150],"domain-general":[152],"problems.Ablation":[153],"studies":[154,164],"confirm":[155],"framework's":[160],"modules,":[161],"visualization":[163],"highlight":[165],"optimal":[166],"deployment":[167],"conditions,":[168],"reinforcing":[169],"conclusions.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-11-28T00:00:00"}