{"id":"https://openalex.org/W2010178645","doi":"https://doi.org/10.3115/1225797.1225804","title":"Document representation and multilevel measures of document similarity","display_name":"Document representation and multilevel measures of document similarity","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2010178645","doi":"https://doi.org/10.3115/1225797.1225804","mag":"2010178645"},"language":"en","primary_location":{"id":"doi:10.3115/1225797.1225804","doi":"https://doi.org/10.3115/1225797.1225804","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1225797.1225804","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1225797.1225804","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology companion volume: doctoral consortium -","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1225797.1225804","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002387873","display_name":"Irina Vladimirovna Matveeva","orcid":"https://orcid.org/0000-0002-8406-6116","observed_orcids":["https://orcid.org/0000-0002-8406-6116","https://orcid.org/0009-0001-1501-3109"]},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Irina Matveeva","raw_affiliation_strings":["University of Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5002387873"],"corresponding_institution_ids":["https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":0.4953,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.53308894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"235","last_page":"238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7612000107765198,"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":0.7612000107765198,"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":0.18039999902248383,"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":0.0215000007301569,"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/document-similarity","display_name":"document similarity","score":0.8740000128746033},{"id":"https://openalex.org/keywords/document-representation","display_name":"document representation","score":0.7749999761581421},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"semantic similarity","score":0.7200000286102295},{"id":"https://openalex.org/keywords/term-similarity","display_name":"term similarity","score":0.6830000281333923},{"id":"https://openalex.org/keywords/graph-based-machine-learning","display_name":"graph-based machine learning","score":0.8999999761581421},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.9430000185966492},{"id":"https://openalex.org/keywords/question-answering","display_name":"question answering","score":0.996999979019165},{"id":"https://openalex.org/keywords/summarization","display_name":"summarization","score":0.8700000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7698460817337036},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6036208868026733},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5896499156951904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5663111209869385},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5634129047393799},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5335208773612976},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.516679048538208},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.5120208859443665},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4932937026023865},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.484421044588089},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48168715834617615},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.43839728832244873},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4319913387298584},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2549556493759155},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1260075867176056},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1225797.1225804","doi":"https://doi.org/10.3115/1225797.1225804","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1225797.1225804","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1225797.1225804","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology companion volume: doctoral consortium -","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.143.6676","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.6676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/N/N06/N06-3007.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1225797.1225804","doi":"https://doi.org/10.3115/1225797.1225804","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1225797.1225804","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1225797.1225804","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology companion volume: doctoral consortium -","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2010178645.pdf","grobid_xml":"https://content.openalex.org/works/W2010178645.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W77146693","https://openalex.org/W1567365482","https://openalex.org/W1956559956","https://openalex.org/W1982050150","https://openalex.org/W2062270497","https://openalex.org/W2093641143","https://openalex.org/W2147152072","https://openalex.org/W2154872931","https://openalex.org/W2166776180","https://openalex.org/W2325227998","https://openalex.org/W2486424789","https://openalex.org/W4245107743","https://openalex.org/W4255198209"],"related_works":["https://openalex.org/W3206371102","https://openalex.org/W1601615061","https://openalex.org/W7097375687","https://openalex.org/W3119537809","https://openalex.org/W1996476189","https://openalex.org/W7100970597","https://openalex.org/W7096217592","https://openalex.org/W1564382496","https://openalex.org/W4287890644","https://openalex.org/W2187633097"],"abstract_inverted_index":{"We":[0],"present":[1],"our":[2],"work":[3],"on":[4],"combining":[5],"large-scale":[6],"statistical":[7],"approaches":[8],"with":[9],"local":[10],"linguistic":[11],"analysis":[12],"and":[13,28,37],"graph-based":[14],"machine":[15],"learning":[16],"techniques":[17],"to":[18],"compute":[19],"a":[20],"combined":[21],"measure":[22],"of":[23],"semantic":[24],"similarity":[25],"between":[26],"terms":[27],"documents":[29],"for":[30],"application":[31],"in":[32],"information":[33],"extraction,":[34],"question":[35],"answering,":[36],"summarisation.":[38]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2013,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}