{"id":"https://openalex.org/W3116203071","doi":"https://doi.org/10.18653/v1/2020.coling-main.482","title":"Unsupervised Fine-tuning for Text Clustering","display_name":"Unsupervised Fine-tuning for Text Clustering","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3116203071","doi":"https://doi.org/10.18653/v1/2020.coling-main.482","mag":"3116203071"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.coling-main.482","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.482","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.482.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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/2020.coling-main.482.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061624006","display_name":"Shaohan Huang","orcid":"https://orcid.org/0000-0003-4324-6337"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shaohan Huang","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014662947","display_name":"Furu Wei","orcid":"https://orcid.org/0000-0002-7810-5852"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Furu Wei","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101581993","display_name":"Lei Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Cui","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343564","display_name":"Xingxing Zhang","orcid":"https://orcid.org/0000-0002-2369-0169"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingxing Zhang","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100701572","display_name":"Ming Zhou","orcid":"https://orcid.org/0000-0002-2551-2964"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Zhou","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061624006"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":0.685,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.77640573,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5530","last_page":"5534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9986000061035156,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.7083995342254639},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6779857873916626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5615893602371216},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3814639151096344},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32723501324653625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7083995342254639},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6779857873916626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5615893602371216},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3814639151096344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32723501324653625}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2020.coling-main.482","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.482","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.482.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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.coling-main.482","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.482","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.482.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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3116203071.pdf","grobid_xml":"https://content.openalex.org/works/W3116203071.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1491343858","https://openalex.org/W1532325895","https://openalex.org/W2037603696","https://openalex.org/W2170240176","https://openalex.org/W2187089797","https://openalex.org/W2533545350","https://openalex.org/W2741943936","https://openalex.org/W2784962210","https://openalex.org/W2884851420","https://openalex.org/W2896457183","https://openalex.org/W2962739339","https://openalex.org/W2963012544","https://openalex.org/W2963026768","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964074409","https://openalex.org/W2989499211","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W1999627569","https://openalex.org/W763609066","https://openalex.org/W2611614995","https://openalex.org/W2368651715","https://openalex.org/W2789919619","https://openalex.org/W1552159754","https://openalex.org/W2148757832","https://openalex.org/W4321496520","https://openalex.org/W2293457016","https://openalex.org/W3107474891"],"abstract_inverted_index":{"Fine-tuning":[0],"with":[1],"pre-trained":[2,31,50],"language":[3,13],"models":[4,32,51],"(e.g.":[5,19],"BERT)":[6],"has":[7,26],"achieved":[8],"great":[9],"success":[10],"in":[11,16,33],"many":[12],"understanding":[14],"tasks":[15],"supervised":[17],"settings":[18],"text":[20,38,54,59,72],"classification).":[21],"However,":[22],"relatively":[23],"little":[24],"work":[25],"been":[27],"focused":[28],"on":[29,70],"applying":[30],"unsupervised":[34],"settings,":[35],"such":[36],"as":[37],"clustering.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"propose":[44],"a":[45,65],"novel":[46],"method":[47],"to":[48],"fine-tune":[49],"unsupervisedly":[52],"for":[53],"clustering,":[55],"which":[56],"simultaneously":[57],"learns":[58],"representations":[60],"and":[61,78,88],"cluster":[62],"assignments":[63],"using":[64],"clustering":[66,73],"oriented":[67],"loss.":[68],"Experiments":[69],"three":[71],"datasets":[74],"(namely":[75],"TREC-6,":[76],"Yelp,":[77],"DBpedia)":[79],"show":[80],"that":[81],"our":[82],"model":[83],"outperforms":[84],"the":[85],"baseline":[86],"methods":[87],"achieves":[89],"stateof-the-art":[90],"results.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}