{"id":"https://openalex.org/W2774940746","doi":"https://doi.org/10.1162/tacl_a_00073","title":"Unsupervised Acquisition of Comprehensive Multiword Lexicons using Competition in an <i>n</i>-gram Lattice","display_name":"Unsupervised Acquisition of Comprehensive Multiword Lexicons using Competition in an <i>n</i>-gram Lattice","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2774940746","doi":"https://doi.org/10.1162/tacl_a_00073","mag":"2774940746"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00073","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00073","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00073","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00073","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087743588","display_name":"Julian Brooke","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Julian Brooke","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne,"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne,","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067851924","display_name":"Jan \u0160najder","orcid":"https://orcid.org/0000-0001-8942-5301"},"institutions":[{"id":"https://openalex.org/I181343428","display_name":"University of Zagreb","ror":"https://ror.org/00mv6sv71","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428"]}],"countries":["HR"],"is_corresponding":true,"raw_author_name":"Jan \u0160najder","raw_affiliation_strings":["Faculty of Electrical Engineering and Computing, University of Zagreb,"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computing, University of Zagreb,","institution_ids":["https://openalex.org/I181343428"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103085805","display_name":"Timothy Baldwin","orcid":"https://orcid.org/0000-0002-4445-1386"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Timothy Baldwin","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne,"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne,","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067851924","https://openalex.org/A5087743588","https://openalex.org/A5103085805"],"corresponding_institution_ids":["https://openalex.org/I165779595","https://openalex.org/I181343428"],"apc_list":null,"apc_paid":null,"fwci":0.2079,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6642743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"5","issue":null,"first_page":"455","last_page":"470"},"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":0.9994000196456909,"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/T12031","display_name":"Speech and dialogue systems","score":0.9944999814033508,"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":0.8368089199066162},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.5930664539337158},{"id":"https://openalex.org/keywords/lattice","display_name":"Lattice (music)","score":0.5620858669281006},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5312069654464722},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5058905482292175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4904029369354248},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3380005359649658}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8368089199066162},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.5930664539337158},{"id":"https://openalex.org/C2781204021","wikidata":"https://www.wikidata.org/wiki/Q6497091","display_name":"Lattice (music)","level":2,"score":0.5620858669281006},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5312069654464722},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5058905482292175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4904029369354248},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3380005359649658},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00073","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00073","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00073","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:175297d1a53e4635b9c649ffdcf71b67","is_oa":true,"landing_page_url":"https://doaj.org/article/175297d1a53e4635b9c649ffdcf71b67","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 5 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00073","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00073","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00073","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1823291719","display_name":null,"funder_award_id":"UIP-2014-09-7312","funder_id":"https://openalex.org/F4320322674","funder_display_name":"Hrvatska Zaklada za Znanost"}],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320322674","display_name":"Hrvatska Zaklada za Znanost","ror":"https://ror.org/03n51vw80"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2774940746.pdf","grobid_xml":"https://content.openalex.org/works/W2774940746.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W47773400","https://openalex.org/W153318553","https://openalex.org/W162266594","https://openalex.org/W634820411","https://openalex.org/W638675188","https://openalex.org/W976440716","https://openalex.org/W1208721423","https://openalex.org/W1498763386","https://openalex.org/W1502101714","https://openalex.org/W1522263329","https://openalex.org/W1527092776","https://openalex.org/W1558866924","https://openalex.org/W1593045043","https://openalex.org/W1964788111","https://openalex.org/W1981231959","https://openalex.org/W2007709031","https://openalex.org/W2036142485","https://openalex.org/W2042380438","https://openalex.org/W2049107599","https://openalex.org/W2057399676","https://openalex.org/W2076766778","https://openalex.org/W2116780029","https://openalex.org/W2118473862","https://openalex.org/W2123215530","https://openalex.org/W2126377586","https://openalex.org/W2141232148","https://openalex.org/W2146316509","https://openalex.org/W2158150553","https://openalex.org/W2168820179","https://openalex.org/W2224490803","https://openalex.org/W2226734577","https://openalex.org/W2250383887","https://openalex.org/W2250452161","https://openalex.org/W2250696297","https://openalex.org/W2250955880","https://openalex.org/W2251026193","https://openalex.org/W2252262936","https://openalex.org/W2285453998","https://openalex.org/W2481467102","https://openalex.org/W2499585162","https://openalex.org/W2507263433","https://openalex.org/W2511102264"],"related_works":["https://openalex.org/W2250909759","https://openalex.org/W2532616038","https://openalex.org/W2624072012","https://openalex.org/W2787311093","https://openalex.org/W2057384730","https://openalex.org/W4307474317","https://openalex.org/W2008468404","https://openalex.org/W2147879411","https://openalex.org/W2132221452","https://openalex.org/W2081295016"],"abstract_inverted_index":{"We":[0,63],"present":[1],"a":[2,38,60,70],"new":[3],"model":[4,33],"for":[5],"acquiring":[6],"comprehensive":[7],"multiword":[8],"lexicons":[9],"from":[10],"large":[11],"corpora":[12,96],"based":[13,41],"on":[14,42],"competition":[15],"among":[16],"n-gram":[17],"candidates.":[18],"In":[19],"contrast":[20],"to":[21],"the":[22,66],"standard":[23],"approach":[24],"of":[25,68,80],"simple":[26],"ranking":[27],"by":[28,89],"association":[29],"measure,":[30],"in":[31,37,52],"our":[32,84],"n-grams":[34,82],"are":[35,57],"arranged":[36],"lattice":[39,71],"structure":[40],"subsumption":[43],"and":[44,76,97],"overlap":[45],"relationships,":[46],"with":[47],"nodes":[48,51],"inhibiting":[49],"other":[50],"their":[53],"vicinity":[54],"when":[55],"they":[56],"selected":[58],"as":[59],"lexical":[61],"item.":[62],"show":[64],"how":[65],"configuration":[67],"such":[69],"can":[72],"be":[73],"optimized":[74],"tractably,":[75],"demonstrate":[77],"using":[78],"annotations":[79],"sampled":[81],"that":[83],"method":[85],"consistently":[86],"outperforms":[87],"alternatives":[88],"at":[90],"least":[91],"0.05":[92],"F-score":[93],"across":[94],"several":[95],"languages.":[98]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
