{"id":"https://openalex.org/W1985497222","doi":"https://doi.org/10.1017/s1351324914000072","title":"Pattern-based unsupervised parsing method","display_name":"Pattern-based unsupervised parsing method","publication_year":2014,"publication_date":"2014-06-04","ids":{"openalex":"https://openalex.org/W1985497222","doi":"https://doi.org/10.1017/s1351324914000072","mag":"1985497222"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324914000072","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324914000072","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005742292","display_name":"Jes\u00fas Santamar\u00eda","orcid":null},"institutions":[{"id":"https://openalex.org/I178450904","display_name":"Universidad Nacional de Educaci\u00f3n a Distancia","ror":"https://ror.org/02msb5n36","country_code":"ES","type":"education","lineage":["https://openalex.org/I178450904"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"JES\u00daS SANTAMAR\u00cdA","raw_affiliation_strings":["Lenguajes y Sistemas Inform\u00e1ticos, Universidad Nacional de Educaci\u00f3n a Distancia (UNED), Madrid 28040, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lenguajes y Sistemas Inform\u00e1ticos, Universidad Nacional de Educaci\u00f3n a Distancia (UNED), Madrid 28040, Spain","institution_ids":["https://openalex.org/I178450904"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076188730","display_name":"Lourdes Araujo","orcid":"https://orcid.org/0000-0002-7657-4794"},"institutions":[{"id":"https://openalex.org/I178450904","display_name":"Universidad Nacional de Educaci\u00f3n a Distancia","ror":"https://ror.org/02msb5n36","country_code":"ES","type":"education","lineage":["https://openalex.org/I178450904"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"LOURDES ARAUJO","raw_affiliation_strings":["Lenguajes y Sistemas Inform\u00e1ticos, Universidad Nacional de Educaci\u00f3n a Distancia (UNED), Madrid 28040, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lenguajes y Sistemas Inform\u00e1ticos, Universidad Nacional de Educaci\u00f3n a Distancia (UNED), Madrid 28040, Spain","institution_ids":["https://openalex.org/I178450904"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005742292"],"corresponding_institution_ids":["https://openalex.org/I178450904"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06503081,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"3","first_page":"397","last_page":"422"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9991999864578247,"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/T11567","display_name":"semigroups and automata theory","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9162329435348511},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.8571120500564575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7313112020492554},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7234699726104736},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5859297513961792},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5320544838905334},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5134623646736145},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5009264945983887},{"id":"https://openalex.org/keywords/parse-tree","display_name":"Parse tree","score":0.4828791916370392},{"id":"https://openalex.org/keywords/hebrew","display_name":"Hebrew","score":0.4518645405769348},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4279959499835968},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12670737504959106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9162329435348511},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8571120500564575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7313112020492554},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7234699726104736},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5859297513961792},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5320544838905334},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5134623646736145},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5009264945983887},{"id":"https://openalex.org/C2781466058","wikidata":"https://www.wikidata.org/wiki/Q627921","display_name":"Parse tree","level":3,"score":0.4828791916370392},{"id":"https://openalex.org/C91304198","wikidata":"https://www.wikidata.org/wiki/Q9288","display_name":"Hebrew","level":2,"score":0.4518645405769348},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4279959499835968},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12670737504959106},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324914000072","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324914000072","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309370","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320323261","display_name":"Universidad Nacional de Educaci\u00f3n a Distancia","ror":"https://ror.org/02msb5n36"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W46355541","https://openalex.org/W82889912","https://openalex.org/W183201499","https://openalex.org/W1495446613","https://openalex.org/W1575798196","https://openalex.org/W1632114991","https://openalex.org/W1865009630","https://openalex.org/W1965364888","https://openalex.org/W2005085483","https://openalex.org/W2024657257","https://openalex.org/W2081228205","https://openalex.org/W2087165009","https://openalex.org/W2110190189","https://openalex.org/W2115803233","https://openalex.org/W2117871943","https://openalex.org/W2132726600","https://openalex.org/W2133924262","https://openalex.org/W2135057643","https://openalex.org/W2139090905","https://openalex.org/W2142523187","https://openalex.org/W2143995218","https://openalex.org/W2144916786","https://openalex.org/W2153568660","https://openalex.org/W2166044723","https://openalex.org/W2180373279","https://openalex.org/W2252272858","https://openalex.org/W2274077911","https://openalex.org/W2491886887","https://openalex.org/W2792932412","https://openalex.org/W6636649193"],"related_works":["https://openalex.org/W4244615522","https://openalex.org/W1972256049","https://openalex.org/W2338828339","https://openalex.org/W2049995120","https://openalex.org/W2166677757","https://openalex.org/W2141288413","https://openalex.org/W3123688778","https://openalex.org/W1634973882","https://openalex.org/W2033808215","https://openalex.org/W1994456160"],"abstract_inverted_index":{"Abstract":[0],"We":[1,98],"have":[2,87,99],"developed":[3],"a":[4,70,101],"heuristic":[5],"method":[6,14,82],"for":[7,108,126],"unsupervised":[8,106],"parsing":[9],"of":[10,20,24,66,72,80,123],"unrestricted":[11],"text.":[12],"Our":[13],"relies":[15],"on":[16,32,83,90],"detecting":[17],"certain":[18],"patterns":[19],"part-of-speech":[21,44],"tag":[22],"sequences":[23],"words":[25],"in":[26,52],"sentences.":[27],"This":[28],"detection":[29],"is":[30],"based":[31],"statistical":[33],"data":[34],"obtained":[35,100],"from":[36],"the":[37,53,63,78,81,120],"corpus":[38],"and":[39,96,113],"allows":[40],"us":[41],"to":[42,61,76],"classify":[43],"tags":[45],"into":[46],"classes":[47,57],"that":[48],"play":[49],"specific":[50],"roles":[51],"parse":[54,64],"trees.":[55],"These":[56],"are":[58],"then":[59],"used":[60],"construct":[62],"tree":[65],"new":[67],"sentences":[68],"via":[69],"set":[71],"deterministic":[73],"rules.":[74],"Aiming":[75],"asses":[77],"viability":[79],"different":[84],"languages,":[85,110],"we":[86,118],"tested":[88],"it":[89],"English,":[91,112],"Spanish,":[92],"Italian,":[93],"Hebrew,":[94],"German,":[95],"Chinese.":[97],"significant":[102],"improvement":[103],"over":[104],"other":[105],"approaches":[107],"some":[109],"including":[111],"provided,":[114],"as":[115,117],"far":[116],"know,":[119],"first":[121],"results":[122],"this":[124],"kind":[125],"others.":[127]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
