{"id":"https://openalex.org/W2080553749","doi":"https://doi.org/10.1142/s0219427901000357","title":"Information Extraction Strategies for Thai Documents","display_name":"Information Extraction Strategies for Thai Documents","publication_year":2001,"publication_date":"2001-06-01","ids":{"openalex":"https://openalex.org/W2080553749","doi":"https://doi.org/10.1142/s0219427901000357","mag":"2080553749"},"language":"en","primary_location":{"id":"doi:10.1142/s0219427901000357","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219427901000357","pdf_url":null,"source":{"id":"https://openalex.org/S50006202","display_name":"International Journal of Computer Processing Of Languages","issn_l":"1793-8406","issn":["1793-8406","2010-0205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Processing of Languages","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/A5072474505","display_name":"Rattasit Sukhahuta","orcid":null},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"RATTASIT SUKHAHUTA","raw_affiliation_strings":["School of Information Systems, University of East Anglia Norwich, NR4 7TJ, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Systems, University of East Anglia Norwich, NR4 7TJ, UK","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109193242","display_name":"DAN SMITH","orcid":null},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"DAN SMITH","raw_affiliation_strings":["School of Information Systems, University of East Anglia Norwich, NR4 7TJ, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Systems, University of East Anglia Norwich, NR4 7TJ, UK","institution_ids":["https://openalex.org/I1118541"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1118541"],"apc_list":null,"apc_paid":null,"fwci":2.3308,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.90384469,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"14","issue":"02","first_page":"153","last_page":"172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10215","display_name":"Semantic Web and Ontologies","score":0.9993000030517578,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9040029048919678},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7909213900566101},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7146167755126953},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6363071799278259},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6037294864654541},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5808352828025818},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5566476583480835},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5544942617416382},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4920627474784851},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4258507490158081},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.42497891187667847},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22755971550941467}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9040029048919678},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7909213900566101},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7146167755126953},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6363071799278259},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6037294864654541},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5808352828025818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5566476583480835},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5544942617416382},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4920627474784851},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4258507490158081},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.42497891187667847},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22755971550941467},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1142/s0219427901000357","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219427901000357","pdf_url":null,"source":{"id":"https://openalex.org/S50006202","display_name":"International Journal of Computer Processing Of Languages","issn_l":"1793-8406","issn":["1793-8406","2010-0205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Processing of Languages","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.23.3690","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.23.3690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.se.cuhk.edu.hk/PEOPLE/../dn/jcpol-p4.pdf","raw_type":"text"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:23606","is_oa":false,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/23606/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1516146643","https://openalex.org/W1518670641","https://openalex.org/W1667964228","https://openalex.org/W1779820454","https://openalex.org/W1882985034","https://openalex.org/W1956559956","https://openalex.org/W1970161214","https://openalex.org/W2008248260","https://openalex.org/W2019509999","https://openalex.org/W2020647130","https://openalex.org/W2051214422","https://openalex.org/W2097847889","https://openalex.org/W2100674109","https://openalex.org/W2164949130","https://openalex.org/W2953014340"],"related_works":["https://openalex.org/W579810227","https://openalex.org/W2952780262","https://openalex.org/W2979495269","https://openalex.org/W2392917763","https://openalex.org/W2083429127","https://openalex.org/W2358855848","https://openalex.org/W2142145894","https://openalex.org/W2033808215","https://openalex.org/W2807110902","https://openalex.org/W2359307945"],"abstract_inverted_index":{"The":[0,47,83],"development":[1],"of":[2,14,32,49,75,86,101,146,167],"an":[3],"information":[4,145],"extraction":[5,141],"(IE)":[6],"system":[7,88],"for":[8,20],"Thai":[9,34,44,51],"documents":[10],"raises":[11],"a":[12,122,165],"number":[13],"issues":[15],"which":[16,55],"are":[17,61],"not":[18],"important":[19],"IE":[21,45,66],"in":[22,68,139,154],"English":[23],"and":[24,35,39,72,114,160],"other":[25],"European":[26,70],"languages.":[27],"We":[28],"describe":[29],"the":[30,36,43,98,102,127,132,140,144,151,162],"characteristics":[31],"written":[33,50],"problem":[37],"statements,":[38],"our":[40],"approach":[41],"to":[42,63,78,90,96,120,156,170],"system.":[46],"structure":[48,100,111],"is":[52,89,119,148],"highly":[53],"ambiguous,":[54],"requires":[56],"more":[57],"sophisticated":[58],"techniques":[59],"than":[60],"necessary":[62],"perform":[64,121],"comparable":[65],"tasks":[67],"most":[69],"languages,":[71],"large":[73],"amounts":[74],"domain":[76],"knowledge":[77],"cope":[79],"with":[80,164],"these":[81],"ambiguities.":[82],"basic":[84],"characteristic":[85],"this":[87],"provide":[91],"di#erent":[92],"natural":[93],"language":[94],"components":[95,105],"assess":[97],"surface":[99],"documents.":[103],"These":[104],"include":[106],"word":[107],"segmentation,":[108],"specific":[109,133],"lexical":[110],"terms":[112,135],"identification":[113],"part-of-speech":[115],"tagger.":[116],"Further":[117],"analysis":[118],"shallow":[123],"parsing":[124],"based":[125],"on":[126],"relevant":[128],"regions":[129],"that":[130],"containing":[131],"trigger":[134],"or":[136],"patterns":[137],"specified":[138],"templates.":[142],"Finally,":[143],"interest":[147],"extracted":[149],"from":[150],"grammar":[152],"trees":[153],"corresponding":[155],"predefined":[157],"concept":[158],"definitions":[159],"returns":[161],"users":[163],"list":[166],"answers":[168],"responding":[169],"each":[171],"concept.":[172],"Keywords:":[173],"Information":[174],"Extraction,":[175],"Morphological":[176],"Analysis,":[177],"Part-of-Speech":[178],"tagger,":[179],"Phrase":[180],"Structure":[181],"Grammar.":[182],"1":[183]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}
