{"id":"https://openalex.org/W2029086132","doi":"https://doi.org/10.1162/coli_a_00170","title":"Sampling Tree Fragments from Forests","display_name":"Sampling Tree Fragments from Forests","publication_year":2013,"publication_date":"2013-06-26","ids":{"openalex":"https://openalex.org/W2029086132","doi":"https://doi.org/10.1162/coli_a_00170","mag":"2029086132"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00170","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00170","pdf_url":"https://direct.mit.edu/coli/article-pdf/40/1/203/1812705/coli_a_00170.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://direct.mit.edu/coli/article-pdf/40/1/203/1812705/coli_a_00170.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047508601","display_name":"Tagyoung Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tagyoung Chung","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004866786","display_name":"Licheng Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Licheng Fang","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020945377","display_name":"Daniel Gildea","orcid":"https://orcid.org/0000-0002-7858-2624"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Gildea","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088287514","display_name":"Daniel \u0160tefankovi\u010d","orcid":"https://orcid.org/0000-0002-4849-7955"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel \u0160tefankovi\u010d","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":3.8942,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93489895,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"40","issue":"1","first_page":"203","last_page":"229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9998000264167786,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9954000115394592,"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":0.7327425479888916},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.7039570212364197},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.5356727242469788},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5336951017379761},{"id":"https://openalex.org/keywords/fractal-tree-index","display_name":"Fractal tree index","score":0.46753212809562683},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.4635182321071625},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45089131593704224},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.4368535876274109},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.4329299330711365},{"id":"https://openalex.org/keywords/regular-tree-grammar","display_name":"Regular tree grammar","score":0.4324128031730652},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42529773712158203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.425123393535614},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4158574044704437},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41031041741371155},{"id":"https://openalex.org/keywords/interval-tree","display_name":"Interval tree","score":0.36769789457321167},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2053760290145874},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.17327600717544556},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.118283212184906},{"id":"https://openalex.org/keywords/phrase-structure-rules","display_name":"Phrase structure rules","score":0.10181728005409241},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10153207182884216},{"id":"https://openalex.org/keywords/binary-tree","display_name":"Binary tree","score":0.08882436156272888},{"id":"https://openalex.org/keywords/mildly-context-sensitive-grammar-formalism","display_name":"Mildly context-sensitive grammar formalism","score":0.07614338397979736}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7327425479888916},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.7039570212364197},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.5356727242469788},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5336951017379761},{"id":"https://openalex.org/C163736687","wikidata":"https://www.wikidata.org/wiki/Q17014592","display_name":"Fractal tree index","level":5,"score":0.46753212809562683},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.4635182321071625},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45089131593704224},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.4368535876274109},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.4329299330711365},{"id":"https://openalex.org/C57097763","wikidata":"https://www.wikidata.org/wiki/Q7309622","display_name":"Regular tree grammar","level":5,"score":0.4324128031730652},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42529773712158203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.425123393535614},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4158574044704437},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41031041741371155},{"id":"https://openalex.org/C84927040","wikidata":"https://www.wikidata.org/wiki/Q6057306","display_name":"Interval tree","level":4,"score":0.36769789457321167},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2053760290145874},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.17327600717544556},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.118283212184906},{"id":"https://openalex.org/C80877019","wikidata":"https://www.wikidata.org/wiki/Q7188074","display_name":"Phrase structure rules","level":3,"score":0.10181728005409241},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10153207182884216},{"id":"https://openalex.org/C197855036","wikidata":"https://www.wikidata.org/wiki/Q380172","display_name":"Binary tree","level":2,"score":0.08882436156272888},{"id":"https://openalex.org/C172265290","wikidata":"https://www.wikidata.org/wiki/Q6134957","display_name":"Mildly context-sensitive grammar formalism","level":4,"score":0.07614338397979736},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1162/coli_a_00170","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00170","pdf_url":"https://direct.mit.edu/coli/article-pdf/40/1/203/1812705/coli_a_00170.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.307.7896","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.307.7896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.rochester.edu/~gildea/pubs/chung-cl13.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.651.556","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.651.556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology/J/J14/J14-1007.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:1f1fdeac59bf460c90517a82f52ec0aa","is_oa":false,"landing_page_url":"https://doaj.org/article/1f1fdeac59bf460c90517a82f52ec0aa","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 40, Iss 1 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00170","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00170","pdf_url":"https://direct.mit.edu/coli/article-pdf/40/1/203/1812705/coli_a_00170.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4171828849","display_name":"RI: Large:Collaborative Research: Richer Representations for Machine Translation","funder_award_id":"0910611","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2029086132.pdf","grobid_xml":"https://content.openalex.org/works/W2029086132.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W222053410","https://openalex.org/W1516184288","https://openalex.org/W1551202288","https://openalex.org/W1607035479","https://openalex.org/W1636598325","https://openalex.org/W1708005048","https://openalex.org/W1763771263","https://openalex.org/W2005234139","https://openalex.org/W2006969979","https://openalex.org/W2007709031","https://openalex.org/W2008225289","https://openalex.org/W2028162617","https://openalex.org/W2038698865","https://openalex.org/W2069931267","https://openalex.org/W2087309226","https://openalex.org/W2096309684","https://openalex.org/W2101105183","https://openalex.org/W2105891181","https://openalex.org/W2108847444","https://openalex.org/W2111142112","https://openalex.org/W2111500764","https://openalex.org/W2112900913","https://openalex.org/W2113939335","https://openalex.org/W2115526192","https://openalex.org/W2123641849","https://openalex.org/W2126270798","https://openalex.org/W2126784652","https://openalex.org/W2133444727","https://openalex.org/W2146574666","https://openalex.org/W2152213375","https://openalex.org/W2152263452","https://openalex.org/W2152600988","https://openalex.org/W2153653739","https://openalex.org/W2154099718","https://openalex.org/W2158388102","https://openalex.org/W2164151151","https://openalex.org/W2165666205","https://openalex.org/W2180952760","https://openalex.org/W2437005631","https://openalex.org/W2591804103","https://openalex.org/W2592549418","https://openalex.org/W2917458986","https://openalex.org/W4206070857","https://openalex.org/W4230870880"],"related_works":["https://openalex.org/W2227684440","https://openalex.org/W2359095153","https://openalex.org/W2280371997","https://openalex.org/W1521720839","https://openalex.org/W2160311168","https://openalex.org/W2083751087","https://openalex.org/W2376256808","https://openalex.org/W2156833871","https://openalex.org/W2343659340","https://openalex.org/W2373110020"],"abstract_inverted_index":{"We":[0,51,105],"study":[1],"the":[2,10,39,42,62,73,87,92],"problem":[3],"of":[4,21,94],"sampling":[5,32],"trees":[6],"from":[7],"forests,":[8,67],"in":[9],"setting":[11,27],"where":[12,41],"probabilities":[13],"for":[14,31,61,81],"each":[15],"tree":[16,24,43],"may":[17],"be":[18],"a":[19,53],"function":[20],"arbitrarily":[22],"large":[23],"fragments.":[25],"This":[26],"extends":[28],"recent":[29],"work":[30],"to":[33,38,75,111],"learn":[34,76],"Tree":[35],"Substitution":[36],"Grammars":[37],"case":[40],"structure":[44],"(TSG":[45],"derived":[46],"tree)":[47],"is":[48],"not":[49],"fixed.":[50],"develop":[52],"Markov":[54],"chain":[55],"Monte":[56],"Carlo":[57],"algorithm":[58,74],"which":[59],"corrects":[60],"bias":[63],"introduced":[64],"by":[65],"unbalanced":[66],"and":[68],"we":[69],"present":[70],"experiments":[71],"using":[72],"Synchronous":[77],"Context-Free":[78],"Grammar":[79],"rules":[80,96],"machine":[82,108],"translation.":[83],"In":[84],"this":[85],"application,":[86],"forests":[88],"being":[89],"sampled":[90],"represent":[91],"set":[93],"Hiero-style":[95],"that":[97],"are":[98],"consistent":[99],"with":[100,115],"fixed":[101],"input":[102],"word-level":[103],"alignments.":[104],"demonstrate":[106],"equivalent":[107],"translation":[109],"performance":[110],"standard":[112],"techniques":[113],"but":[114],"much":[116],"smaller":[117],"grammars.":[118]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}