{"id":"https://openalex.org/W2070237816","doi":"https://doi.org/10.1109/iucs.2010.5666227","title":"Unsupervised text pattern learning using minimum description length","display_name":"Unsupervised text pattern learning using minimum description length","publication_year":2010,"publication_date":"2010-10-01","ids":{"openalex":"https://openalex.org/W2070237816","doi":"https://doi.org/10.1109/iucs.2010.5666227","mag":"2070237816"},"language":"en","primary_location":{"id":"doi:10.1109/iucs.2010.5666227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iucs.2010.5666227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 4th International Universal Communication Symposium","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/A5103511602","display_name":"Ke Wu","orcid":"https://orcid.org/0009-0006-9925-3834"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Wu","raw_affiliation_strings":["Department of Computer Science and Technology, School of Electronics Engineering and Computer Science, Key Laboratory of High Confidence Software Technologies, Ministry of Education, Peking University, Beijing, China","Department of Computer Science and Technology, School of Electronics Engineering and Computer Science, Keylaboratory of High Confidence Software Technologies, Ministry of Education, Peking University, Beijing 100871, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, School of Electronics Engineering and Computer Science, Key Laboratory of High Confidence Software Technologies, Ministry of Education, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Department of Computer Science and Technology, School of Electronics Engineering and Computer Science, Keylaboratory of High Confidence Software Technologies, Ministry of Education, Peking University, Beijing 100871, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028209642","display_name":"Jiangsheng Yu","orcid":"https://orcid.org/0000-0001-6050-3994"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangsheng Yu","raw_affiliation_strings":["Department of Computer Science and Technology, School of Electronics Engineering and Computer Science, Key Laboratory of High Confidence Software Technologies, Ministry of Education, Peking University, Beijing, China","Department of Computer Science and Technology, School of Electronics Engineering and Computer Science, Keylaboratory of High Confidence Software Technologies, Ministry of Education, Peking University, Beijing 100871, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, School of Electronics Engineering and Computer Science, Key Laboratory of High Confidence Software Technologies, Ministry of Education, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Department of Computer Science and Technology, School of Electronics Engineering and Computer Science, Keylaboratory of High Confidence Software Technologies, Ministry of Education, Peking University, Beijing 100871, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079106687","display_name":"Hanpin Wang","orcid":"https://orcid.org/0000-0002-2439-1670"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanpin Wang","raw_affiliation_strings":["Department of Computer Science and Technology, School of Electronics Engineering and Computer Science, Key Laboratory of High Confidence Software Technologies, Ministry of Education, Peking University, Beijing, China","Department of Computer Science and Technology, School of Electronics Engineering and Computer Science, Keylaboratory of High Confidence Software Technologies, Ministry of Education, Peking University, Beijing 100871, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, School of Electronics Engineering and Computer Science, Key Laboratory of High Confidence Software Technologies, Ministry of Education, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Department of Computer Science and Technology, School of Electronics Engineering and Computer Science, Keylaboratory of High Confidence Software Technologies, Ministry of Education, Peking University, Beijing 100871, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101451435","display_name":"Fei Cheng","orcid":"https://orcid.org/0000-0001-5161-0544"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Cheng","raw_affiliation_strings":["Department of Mathematics, Beijing Jiaotong University, Beijing, China","Department of Mathematics, Beijing Jiaotong University, 100044 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Department of Mathematics, Beijing Jiaotong University, 100044 China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"161","last_page":"166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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"}},{"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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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":0.8326406478881836},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"Minimum description length","score":0.8173187375068665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6967326402664185},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6300191879272461},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6040869355201721},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5802698135375977},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5717378854751587},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.522731602191925},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4851594567298889},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.47453391551971436},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.47009870409965515},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.46439698338508606},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08901581168174744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8326406478881836},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.8173187375068665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6967326402664185},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6300191879272461},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6040869355201721},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5802698135375977},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5717378854751587},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.522731602191925},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4851594567298889},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.47453391551971436},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.47009870409965515},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.46439698338508606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08901581168174744},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iucs.2010.5666227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iucs.2010.5666227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 4th International Universal Communication Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8799999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1779834323","https://openalex.org/W1968908999","https://openalex.org/W2095734615","https://openalex.org/W2101460669","https://openalex.org/W2101711363","https://openalex.org/W2123215530","https://openalex.org/W2125504873","https://openalex.org/W2135479443","https://openalex.org/W2136309948","https://openalex.org/W2166089232","https://openalex.org/W3123545922"],"related_works":["https://openalex.org/W4298831272","https://openalex.org/W2489956408","https://openalex.org/W349256592","https://openalex.org/W2086694237","https://openalex.org/W4213307346","https://openalex.org/W2037989911","https://openalex.org/W2068210614","https://openalex.org/W2130372067","https://openalex.org/W32469337","https://openalex.org/W2150143935"],"abstract_inverted_index":{"The":[0],"knowledge":[1],"of":[2,42,72],"text":[3,43],"patterns":[4,73],"in":[5,11],"a":[6,31],"domain-specific":[7],"corpus":[8,67],"is":[9,57],"valuable":[10],"many":[12],"natural":[13],"language":[14,36],"processing":[15],"(NLP)":[16],"applications":[17],"such":[18],"as":[19],"information":[20],"extraction,":[21],"question-answering":[22],"system,":[23],"and":[24,59],"etc.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29],"propose":[30],"simple":[32],"but":[33],"effective":[34],"probabilistic":[35],"model":[37],"for":[38],"modeling":[39],"the":[40,46,60],"in-decomposability":[41],"patterns.":[44],"Under":[45],"minimum":[47],"description":[48],"length":[49],"(MDL)":[50],"principle,":[51],"an":[52,63],"efficient":[53],"unsupervised":[54],"learning":[55],"algorithm":[56],"implemented":[58],"experiment":[61],"on":[62],"English":[64],"critical":[65],"writing":[66],"has":[68],"shown":[69],"promising":[70],"coverage":[71],"compared":[74],"with":[75],"human":[76],"summary.":[77]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}