{"id":"https://openalex.org/W2126385423","doi":"https://doi.org/10.3115/1118693.1118715","title":"Bootstrapping lexical choice via multiple-sequence alignment","display_name":"Bootstrapping lexical choice via multiple-sequence alignment","publication_year":2002,"publication_date":"2002-01-01","ids":{"openalex":"https://openalex.org/W2126385423","doi":"https://doi.org/10.3115/1118693.1118715","mag":"2126385423"},"language":"en","primary_location":{"id":"doi:10.3115/1118693.1118715","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118715","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118715","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing - EMNLP '02","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118715","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010124873","display_name":"Regina Barzilay","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Regina Barzilay","raw_affiliation_strings":["Columbia University, New York, NY","Columbia University, New York, NY;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York, NY;","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076876084","display_name":"Lillian Lee","orcid":"https://orcid.org/0000-0003-4770-1712"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lillian Lee","raw_affiliation_strings":["Cornell University, Ithaca, NY","Cornell University (Ithaca, NY);"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Cornell University (Ithaca, NY);","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2106,"has_fulltext":true,"cited_by_count":79,"citation_normalized_percentile":{"value":0.95456763,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"10","issue":null,"first_page":"164","last_page":"171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987999796867371,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.98089998960495,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8377219438552856},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.7302066683769226},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6727418899536133},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6720997095108032},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.6639289855957031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6324737071990967},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5677173137664795},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5391334295272827},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.529691755771637},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.505240261554718},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.48567330837249756},{"id":"https://openalex.org/keywords/lexical-choice","display_name":"Lexical choice","score":0.4592963755130768},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.31692829728126526},{"id":"https://openalex.org/keywords/lexical-item","display_name":"Lexical item","score":0.22743597626686096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8377219438552856},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.7302066683769226},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6727418899536133},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6720997095108032},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6639289855957031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6324737071990967},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5677173137664795},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5391334295272827},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.529691755771637},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.505240261554718},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.48567330837249756},{"id":"https://openalex.org/C93258239","wikidata":"https://www.wikidata.org/wiki/Q6537688","display_name":"Lexical choice","level":3,"score":0.4592963755130768},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.31692829728126526},{"id":"https://openalex.org/C126706616","wikidata":"https://www.wikidata.org/wiki/Q2944660","display_name":"Lexical item","level":2,"score":0.22743597626686096},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.3115/1118693.1118715","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118715","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118715","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing - EMNLP '02","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.10.8160","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.8160","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/W/W02/W02-1022.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.17.4916","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.17.4916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cornell.edu/home/llee/papers/gen-msa.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.8555","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.8555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.columbia.edu/nlp/papers/2002/barzilay_lee_02.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.341.7400","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.341.7400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/cs/0205065v1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.59.8189","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.8189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.columbia.edu/nlp/papers/2002/barzilay_lee_02.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.88.601","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.88.601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cornell.edu/home/llee/papers/gen-msa.pdf","raw_type":"text"},{"id":"doi:10.7916/d8s4719n","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8s4719n","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.3115/1118693.1118715","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118715","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118715","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing - EMNLP '02","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6078825138","display_name":"ITR:  The Construction and Analysis of Information Networks","funder_award_id":"0081334","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2126385423.pdf","grobid_xml":"https://content.openalex.org/works/W2126385423.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W107937452","https://openalex.org/W1518357715","https://openalex.org/W1537860183","https://openalex.org/W1574174742","https://openalex.org/W1630833108","https://openalex.org/W1645937837","https://openalex.org/W1973923101","https://openalex.org/W1990061958","https://openalex.org/W1991035026","https://openalex.org/W2002638840","https://openalex.org/W2004637830","https://openalex.org/W2006969979","https://openalex.org/W2028323959","https://openalex.org/W2033389948","https://openalex.org/W2060956631","https://openalex.org/W2101105183","https://openalex.org/W2107130271","https://openalex.org/W2108239140","https://openalex.org/W2138753018","https://openalex.org/W2201007611","https://openalex.org/W2320748401","https://openalex.org/W2577557087","https://openalex.org/W2594610113","https://openalex.org/W2785456784","https://openalex.org/W2949465329","https://openalex.org/W2953196668","https://openalex.org/W3214380909","https://openalex.org/W4245668478","https://openalex.org/W4292763141"],"related_works":["https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W2370831213","https://openalex.org/W4315704968","https://openalex.org/W4285478380","https://openalex.org/W2100255360","https://openalex.org/W2032810564","https://openalex.org/W2109941374","https://openalex.org/W2134032133"],"abstract_inverted_index":{"An":[0],"important":[1],"component":[2],"of":[3,13,69,85,122],"any":[4],"generation":[5,125],"system":[6,109],"is":[7],"the":[8,30,70,117],"mapping":[9],"dictionary,":[10],"a":[11,40,47,94,104,123],"lexicon":[12],"elementary":[14],"semantic":[15,118],"expressions":[16],"and":[17,96,114],"corresponding":[18,71],"natural":[19,82],"language":[20,83],"realizations.":[21],"Typically,":[22],"labor-intensive":[23],"knowledge-based":[24],"methods":[25],"are":[26],"used":[27,50,77],"to":[28,35,80,116],"construct":[29],"dictionary.":[31],"We":[32],"instead":[33],"propose":[34],"acquire":[36],"it":[37],"automatically":[38],"via":[39],"novel":[41],"multiple-pass":[42],"algorithm":[43],"employing":[44],"multiple-sequence":[45],"alignment,":[46],"technique":[48],"commonly":[49],"in":[51,60,101],"bioinformatics.":[52],"Crucially,":[53],"our":[54,78,108],"method":[55],"lever-ages":[56],"latent":[57],"information":[58],"contained":[59],"multi-parallel":[61],"corpora":[62],"---":[63],"datasets":[64],"that":[65,121],"supply":[66],"several":[67],"verbalizations":[68],"semantics":[72],"rather":[73],"than":[74],"just":[75],"one.We":[76],"techniques":[79],"generate":[81],"versions":[84],"computer-generated":[86],"mathematical":[87],"proofs,":[88],"with":[89],"good":[90],"results":[91],"on":[92],"both":[93],"per-component":[95],"overall-output":[97],"basis.":[98],"For":[99],"example,":[100],"evaluations":[102],"involving":[103],"dozen":[105],"human":[106],"judges,":[107],"produced":[110],"output":[111],"whose":[112],"readability":[113],"faithfulness":[115],"input":[119],"rivaled":[120],"traditional":[124],"system.":[126]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2025-10-10T00:00:00"}