{"id":"https://openalex.org/W4408352993","doi":"https://doi.org/10.1109/icassp49660.2025.10888614","title":"Semi-Supervised Multilingual Alignment with Lexical Memory for Massively Parallel Text Mining","display_name":"Semi-Supervised Multilingual Alignment with Lexical Memory for Massively Parallel Text Mining","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352993","doi":"https://doi.org/10.1109/icassp49660.2025.10888614"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042203856","display_name":"Weitai Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weitai Zhang","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027981943","display_name":"Peiwang Tang","orcid":"https://orcid.org/0000-0003-3681-0761"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peiwang Tang","raw_affiliation_strings":["iFLYTEK Research,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111533843","display_name":"Chao Lin","orcid":"https://orcid.org/0009-0008-1187-5108"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Lin","raw_affiliation_strings":["iFLYTEK Research,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594391","display_name":"Simran Naagar","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Simran Naagar","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087587703","display_name":"Zhongyi Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyi Ye","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741940","display_name":"Junhua Liu","orcid":"https://orcid.org/0000-0003-1460-7244"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhua Liu","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.02592389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9259999990463257,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9259999990463257,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9020000100135803,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8310716152191162},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.6203633546829224},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5565739870071411},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4498519003391266},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.30385687947273254}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8310716152191162},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.6203633546829224},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5565739870071411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4498519003391266},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.30385687947273254}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2105482032","https://openalex.org/W2107695330","https://openalex.org/W2157331557","https://openalex.org/W2513768144","https://openalex.org/W2517504876","https://openalex.org/W2742155240","https://openalex.org/W2759183967","https://openalex.org/W2798389157","https://openalex.org/W2933138175","https://openalex.org/W2962735107","https://openalex.org/W2962784628","https://openalex.org/W2970156971","https://openalex.org/W2970279348","https://openalex.org/W2973088264","https://openalex.org/W3035390927","https://openalex.org/W3037536473","https://openalex.org/W3039695075","https://openalex.org/W3090350559","https://openalex.org/W3105214104","https://openalex.org/W3153073450","https://openalex.org/W3169369929","https://openalex.org/W3173190788","https://openalex.org/W3175301726","https://openalex.org/W3193077216","https://openalex.org/W4300191749","https://openalex.org/W6600880057","https://openalex.org/W6675091423","https://openalex.org/W6731744468","https://openalex.org/W6739901393","https://openalex.org/W6745388339","https://openalex.org/W6755207826","https://openalex.org/W6759455113"],"related_works":["https://openalex.org/W2023839151","https://openalex.org/W1774183074","https://openalex.org/W2057488824","https://openalex.org/W2334687145","https://openalex.org/W2178011914","https://openalex.org/W4235962491","https://openalex.org/W2061778832","https://openalex.org/W1513001507","https://openalex.org/W2257153718","https://openalex.org/W3134702077"],"abstract_inverted_index":{"Existing":[0],"state-of-the-art":[1,136],"techniques":[2],"that":[3,98,126],"employ":[4],"multilingual":[5],"sentence":[6,56],"embeddings":[7,57],"for":[8],"mining":[9],"parallel":[10,28,43,81,117],"texts":[11,44],"predominantly":[12],"rely":[13],"on":[14,77],"extensive":[15],"supervision,":[16],"which":[17],"often":[18],"results":[19,124],"in":[20,23,139],"sub-optimal":[21],"performance":[22,91],"the":[24,89,109,127],"absence":[25],"of":[26,66,74,111],"large-scale":[27],"training":[29,61,96],"datasets.":[30],"In":[31],"this":[32],"study,":[33],"we":[34,87],"introduce":[35],"a":[36,59,71,78],"novel":[37],"method":[38,113,129],"designed":[39],"to":[40,114],"extract":[41],"high-quality":[42,116],"from":[45],"monolingual":[46],"corpora,":[47],"particularly":[48],"targeting":[49],"zero-and":[50,140],"low-resource":[51,141],"languages.":[52],"We":[53,107],"learn":[54],"language-agnostic":[55],"with":[58,119],"two-tiered":[60],"regimen:":[62],"an":[63,94],"initial":[64],"phase":[65,73],"lexical":[67],"knowledge-enhanced":[68],"pretraining":[69],"and":[70,103,132],"subsequent":[72],"supervised":[75,137],"fine-tuning":[76],"minimally":[79],"sized":[80],"dataset":[82],"using":[83],"contrastive":[84],"loss.":[85],"Furthermore,":[86],"enhance":[88],"model\u2019s":[90],"by":[92],"adopting":[93],"iterative":[95],"methodology":[97],"leverages":[99],"both":[100],"mined":[101],"data":[102],"synthetically":[104],"augmented":[105],"data.":[106],"illustrate":[108],"capability":[110],"our":[112],"create":[115],"text":[118],"various":[120],"downstream":[121],"tasks.":[122],"All":[123],"suggest":[125],"proposed":[128],"is":[130],"effective":[131],"can":[133],"surpass":[134],"previous":[135],"methods":[138],"scenarios.":[142]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}