{"id":"https://openalex.org/W2104225263","doi":"https://doi.org/10.3115/1034678.1034734","title":"Less is more","display_name":"Less is more","publication_year":1999,"publication_date":"1999-01-01","ids":{"openalex":"https://openalex.org/W2104225263","doi":"https://doi.org/10.3115/1034678.1034734","mag":"2104225263"},"language":"en","primary_location":{"id":"doi:10.3115/1034678.1034734","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034734","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034734","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034734","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046709688","display_name":"Simon Corston-Oliver","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simon H. Corston-Oliver","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043163116","display_name":"William B. Dolan","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William B. Dolan","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"349","last_page":"356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9970999956130981,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9970999956130981,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.994700014591217,"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":0.9941999912261963,"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/encyclopedia","display_name":"Encyclopedia","score":0.8309744596481323},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.8094638586044312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7693275809288025},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.7556419372558594},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7420458793640137},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.6072383522987366},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5595288276672363},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5228917002677917},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4477894902229309},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3678886294364929},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3526562452316284},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14217150211334229},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.09777653217315674}],"concepts":[{"id":"https://openalex.org/C148863701","wikidata":"https://www.wikidata.org/wiki/Q5292","display_name":"Encyclopedia","level":2,"score":0.8309744596481323},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8094638586044312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7693275809288025},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.7556419372558594},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7420458793640137},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.6072383522987366},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5595288276672363},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5228917002677917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4477894902229309},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3678886294364929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3526562452316284},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14217150211334229},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.09777653217315674},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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:10.3115/1034678.1034734","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034734","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034734","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1034678.1034734","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034734","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034734","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2104225263.pdf","grobid_xml":"https://content.openalex.org/works/W2104225263.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W11171803","https://openalex.org/W164524185","https://openalex.org/W1535954793","https://openalex.org/W1600739331","https://openalex.org/W1864657091","https://openalex.org/W2032083037","https://openalex.org/W2045577803","https://openalex.org/W2045738181","https://openalex.org/W2085891175","https://openalex.org/W2568985560","https://openalex.org/W2726585279","https://openalex.org/W2915677652","https://openalex.org/W2917152527","https://openalex.org/W3008490399","https://openalex.org/W4211258129","https://openalex.org/W4230562832","https://openalex.org/W4405107181","https://openalex.org/W6606627670","https://openalex.org/W6671947044","https://openalex.org/W6732210489"],"related_works":["https://openalex.org/W2348562996","https://openalex.org/W4387776128","https://openalex.org/W3010321750","https://openalex.org/W4394774294","https://openalex.org/W3159833212","https://openalex.org/W4244686159","https://openalex.org/W3011873497","https://openalex.org/W3007654203","https://openalex.org/W2358294942","https://openalex.org/W4367460280"],"abstract_inverted_index":{"We":[0],"perform":[1],"a":[2,41],"linguistic":[3],"analysis":[4],"of":[5,43],"documents":[6],"during":[7],"indexing":[8],"for":[9,38],"information":[10],"retrieval.":[11],"By":[12],"eliminating":[13],"index":[14,22],"terms":[15],"that":[16],"occur":[17],"only":[18],"in":[19],"subordinate":[20],"clauses,":[21],"size":[23],"is":[24],"reduced":[25],"by":[26],"approximately":[27],"30%":[28],"without":[29],"adversely":[30],"affecting":[31],"precision":[32],"or":[33],"recall.":[34],"These":[35],"results":[36],"hold":[37],"two":[39],"corpora:":[40],"sample":[42],"the":[44],"world":[45],"wide":[46],"web":[47],"and":[48],"an":[49],"electronic":[50],"encyclopedia.":[51]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}