{"id":"https://openalex.org/W4382618973","doi":"https://doi.org/10.48550/arxiv.2306.16176","title":"SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills","display_name":"SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills","publication_year":2023,"publication_date":"2023-06-28","ids":{"openalex":"https://openalex.org/W4382618973","doi":"https://doi.org/10.48550/arxiv.2306.16176"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2306.16176","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.16176","pdf_url":"https://arxiv.org/pdf/2306.16176","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.16176","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007059246","display_name":"Zhangyin Feng","orcid":"https://orcid.org/0000-0001-5909-1339"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Feng, Zhangyin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032341066","display_name":"Yong Dai","orcid":"https://orcid.org/0000-0002-6840-9158"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Yong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048926030","display_name":"Fan Zhang","orcid":"https://orcid.org/0000-0002-9501-8478"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Fan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110628758","display_name":"Duyu Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Duyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073213620","display_name":"Xiaocheng Feng","orcid":"https://orcid.org/0000-0001-6011-0496"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Xiaocheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091839641","display_name":"Shuangzhi Wu","orcid":"https://orcid.org/0000-0002-6371-9720"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Shuangzhi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017671620","display_name":"Bing Qin","orcid":"https://orcid.org/0000-0002-2543-5604"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Bing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011542448","display_name":"Yunbo Cao","orcid":"https://orcid.org/0009-0005-2558-5206"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Yunbo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087920747","display_name":"Shuming Shi","orcid":"https://orcid.org/0000-0001-7018-0682"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Shuming","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5007059246"],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9977999925613403,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9735999703407288,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8120415210723877},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.7510063648223877},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6846765875816345},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5768097043037415},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5307942032814026},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5307497978210449},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4984157085418701},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4947175681591034},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42909878492355347},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4113152325153351},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37321212887763977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8120415210723877},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.7510063648223877},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6846765875816345},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5768097043037415},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5307942032814026},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5307497978210449},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4984157085418701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4947175681591034},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42909878492355347},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4113152325153351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37321212887763977},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2306.16176","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.16176","pdf_url":"https://arxiv.org/pdf/2306.16176","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2306.16176","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2306.16176","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2306.16176","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.16176","pdf_url":"https://arxiv.org/pdf/2306.16176","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.8600000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382618973.pdf","grobid_xml":"https://content.openalex.org/works/W4382618973.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W4287598411","https://openalex.org/W3094871513","https://openalex.org/W3100913109","https://openalex.org/W3198458223","https://openalex.org/W3126642501"],"abstract_inverted_index":{"Traditional":[0],"multitask":[1,27,142],"learning":[2,143],"methods":[3],"basically":[4],"can":[5],"only":[6],"exploit":[7],"common":[8],"knowledge":[9,85,95,98],"in":[10,128],"task-":[11],"or":[12,18,79],"language-wise,":[13],"which":[14,31,57,71],"lose":[15],"either":[16,74],"cross-language":[17],"cross-task":[19],"knowledge.":[20],"This":[21],"paper":[22],"proposes":[23],"a":[24,33,60],"general":[25],"multilingual":[26],"model,":[28,171],"named":[29],"SkillNet-X,":[30],"enables":[32],"single":[34],"model":[35,148],"to":[36,59,75,115],"tackle":[37],"many":[38],"different":[39,42],"tasks":[40,178],"from":[41],"languages.":[43,130],"To":[44,165],"this":[45],"end,":[46],"we":[47,103,172],"define":[48],"several":[49],"language-specific":[50],"skills":[51],"and":[52,96,109,140,149,179],"task-specific":[53,138],"skills,":[54],"each":[55],"of":[56,67,92,159,169],"corresponds":[58],"skill":[61,69,88,117,153],"module.":[62],"SkillNet-X":[63,121,134,160,182],"sparsely":[64],"activates":[65],"parts":[66],"the":[68,76,80,105,110,157,167],"modules":[70,89],"are":[72,90],"relevant":[73],"target":[77,81],"task":[78],"language.":[82],"Acting":[83],"as":[84],"transit":[86],"hubs,":[87],"capable":[91],"absorbing":[93],"task-related":[94],"language-related":[97],"consecutively.":[99],"Based":[100],"on":[101,122,161,175],"Transformer,":[102],"modify":[104],"multi-head":[106],"attention":[107],"layer":[108,114],"feed":[111],"forward":[112],"network":[113],"accommodate":[116],"modules.":[118],"We":[119],"evaluate":[120],"eleven":[123],"natural":[124],"language":[125],"understanding":[126],"datasets":[127],"four":[129],"Results":[131],"show":[132],"that":[133,181],"performs":[135],"better":[136],"than":[137],"baselines":[139,144],"two":[141,176],"(i.e.,":[145],"dense":[146],"joint":[147],"Mixture-of-Experts":[150],"model).":[151],"Furthermore,":[152],"pre-training":[154],"further":[155],"improves":[156],"performance":[158],"almost":[162],"all":[163],"datasets.":[164],"investigate":[166],"generalization":[168],"our":[170],"conduct":[173],"experiments":[174],"new":[177],"find":[180],"significantly":[183],"outperforms":[184],"baselines.":[185]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}