{"id":"https://openalex.org/W2000386371","doi":"https://doi.org/10.1016/s0306-4573(01)00044-9","title":"Integrated multi-strategic Web document pre-processing for sentence and word boundary detection","display_name":"Integrated multi-strategic Web document pre-processing for sentence and word boundary detection","publication_year":2002,"publication_date":"2002-07-01","ids":{"openalex":"https://openalex.org/W2000386371","doi":"https://doi.org/10.1016/s0306-4573(01)00044-9","mag":"2000386371"},"language":"en","primary_location":{"id":"doi:10.1016/s0306-4573(01)00044-9","doi":"https://doi.org/10.1016/s0306-4573(01)00044-9","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0306-4573(01)00044-9","pdf_url":null,"source":{"id":"https://openalex.org/S174847851","display_name":"Information Processing & Management","issn_l":"0020-0271","issn":["0020-0271","0306-4573","1873-5371","1878-4089"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","fnege-3","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Processing &amp; Management","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5054825080","display_name":"Junhyeok Shim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junhyeok Shim","raw_affiliation_strings":["NLP Laboratory, Department of CSE in Pohang University of Science & Technology, San 31, Hyoja, Pohang 790-784, South Korea","NLP Laboratory, Department of CSE in Pohang University of Science & Technology, San 31, Hyoja, Pohang 790-784, South Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLP Laboratory, Department of CSE in Pohang University of Science & Technology, San 31, Hyoja, Pohang 790-784, South Korea","institution_ids":["https://openalex.org/I123900574"]},{"raw_affiliation_string":"NLP Laboratory, Department of CSE in Pohang University of Science & Technology, San 31, Hyoja, Pohang 790-784, South Korea#TAB#","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100745975","display_name":"Dongseok Kim","orcid":"https://orcid.org/0000-0002-9876-3393","observed_orcids":["https://orcid.org/0000-0002-9876-3393"]},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongseok Kim","raw_affiliation_strings":["NLP Laboratory, Department of CSE in Pohang University of Science & Technology, San 31, Hyoja, Pohang 790-784, South Korea","NLP Laboratory, Department of CSE in Pohang University of Science & Technology, San 31, Hyoja, Pohang 790-784, South Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLP Laboratory, Department of CSE in Pohang University of Science & Technology, San 31, Hyoja, Pohang 790-784, South Korea","institution_ids":["https://openalex.org/I123900574"]},{"raw_affiliation_string":"NLP Laboratory, Department of CSE in Pohang University of Science & Technology, San 31, Hyoja, Pohang 790-784, South Korea#TAB#","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109869190","display_name":"Jeong-Won Cha","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongwon Cha","raw_affiliation_strings":["NLP Laboratory, Department of CSE in Pohang University of Science & Technology, San 31, Hyoja, Pohang 790-784, South Korea","NLP Laboratory, Department of CSE in Pohang University of Science & Technology, San 31, Hyoja, Pohang 790-784, South Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLP Laboratory, Department of CSE in Pohang University of Science & Technology, San 31, Hyoja, Pohang 790-784, South Korea","institution_ids":["https://openalex.org/I123900574"]},{"raw_affiliation_string":"NLP Laboratory, Department of CSE in Pohang University of Science & Technology, San 31, Hyoja, Pohang 790-784, South Korea#TAB#","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045508648","display_name":"Gary Geunbae Lee","orcid":"https://orcid.org/0000-0002-3692-6732","observed_orcids":["https://orcid.org/0000-0002-3692-6732","https://orcid.org/0000-0003-4788-0140"]},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Gary Geunbae Lee","raw_affiliation_strings":["NLP Laboratory, Department of CSE in Pohang University of Science & Technology, San 31, Hyoja, Pohang 790-784, South Korea","NLP Laboratory, Department of CSE in Pohang University of Science & Technology, San 31, Hyoja, Pohang 790-784, South Korea and CSLI Visiting Researcher, Stanford University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLP Laboratory, Department of CSE in Pohang University of Science & Technology, San 31, Hyoja, Pohang 790-784, South Korea","institution_ids":["https://openalex.org/I123900574"]},{"raw_affiliation_string":"NLP Laboratory, Department of CSE in Pohang University of Science & Technology, San 31, Hyoja, Pohang 790-784, South Korea and CSLI Visiting Researcher, Stanford University, USA","institution_ids":["https://openalex.org/I123900574","https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101975931","display_name":"Jungyun Seo","orcid":"https://orcid.org/0000-0003-3670-7334","observed_orcids":["https://orcid.org/0000-0003-3670-7334","https://orcid.org/0009-0004-3083-9541"]},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jungyun Seo","raw_affiliation_strings":["Department of Computer Science, Sogang University, Sinsu 1-1, Mapo, Seoul 121-742, South Korea","Department of Computer Science, Sogang University, Sinsu 1-1, Mapo, Seoul 121-742, South Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Sogang University, Sinsu 1-1, Mapo, Seoul 121-742, South Korea","institution_ids":["https://openalex.org/I148751991"]},{"raw_affiliation_string":"Department of Computer Science, Sogang University, Sinsu 1-1, Mapo, Seoul 121-742, South Korea#TAB#","institution_ids":["https://openalex.org/I148751991"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101975931"],"corresponding_institution_ids":["https://openalex.org/I148751991"],"apc_list":{"value":3670,"currency":"USD","value_usd":3670},"apc_paid":null,"fwci":1.3475,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81682557,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"4","first_page":"509","last_page":"527"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9970999956130981,"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":0.9970999956130981,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.0007999999797903001,"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":0.0005000000237487257,"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/text-segmentation","display_name":"text segmentation","score":0.6110000014305115},{"id":"https://openalex.org/keywords/html-documents","display_name":"HTML documents","score":0.8989999890327454},{"id":"https://openalex.org/keywords/c4-5-decision-tree","display_name":"C4.5 decision tree","score":0.8199999928474426},{"id":"https://openalex.org/keywords/regular-expressions","display_name":"regular expressions","score":0.6359999775886536},{"id":"https://openalex.org/keywords/heuristic-rules","display_name":"heuristic rules","score":0.699999988079071},{"id":"https://openalex.org/keywords/n-gram-features","display_name":"n-gram features","score":0.7020000219345093},{"id":"https://openalex.org/keywords/morphological-analysis","display_name":"morphological analysis","score":0.796999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.815579891204834},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.7708037495613098},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7219773530960083},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7105235457420349},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6756214499473572},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6075060367584229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6068798303604126},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4842652678489685},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4357762932777405},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4169206917285919},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4033347964286804},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1724170744419098},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":3,"locations":[{"id":"doi:10.1016/s0306-4573(01)00044-9","doi":"https://doi.org/10.1016/s0306-4573(01)00044-9","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0306-4573(01)00044-9","pdf_url":null,"source":{"id":"https://openalex.org/S174847851","display_name":"Information Processing & Management","issn_l":"0020-0271","issn":["0020-0271","0306-4573","1873-5371","1878-4089"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","fnege-3","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Processing &amp; Management","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.106.5989","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.106.5989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nlp.sogang.ac.kr/pub/international/sdarticle.pdf","raw_type":"text"},{"id":"pmh:oai:oasis.postech.ac.kr:2014.oak/19095","doi":null,"is_oa":false,"landing_page_url":"https://oasis.postech.ac.kr/handle/2014.oak/19095","pdf_url":null,"source":{"id":"https://openalex.org/S4306401965","display_name":"Open Access System for Information Sharing (Pohang University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I123900574","host_organization_name":"Pohang University of Science and Technology","host_organization_lineage":["https://openalex.org/I123900574"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1490831147","https://openalex.org/W1773803948","https://openalex.org/W1999051122","https://openalex.org/W2121455532","https://openalex.org/W2144896964","https://openalex.org/W3024750336","https://openalex.org/W3081911444","https://openalex.org/W4205807230"],"related_works":["https://openalex.org/W2393939403","https://openalex.org/W2133065881","https://openalex.org/W1490831147","https://openalex.org/W2107770936","https://openalex.org/W7096643910","https://openalex.org/W1928037164","https://openalex.org/W2159244590","https://openalex.org/W3088908336","https://openalex.org/W4293863309","https://openalex.org/W2353003434"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2016-06-24T00:00:00"}
