{"id":"https://openalex.org/W2065568440","doi":"https://doi.org/10.1016/s0306-4379(98)00027-1","title":"Generating finite-state transducers for semi-structured data extraction from the Web","display_name":"Generating finite-state transducers for semi-structured data extraction from the Web","publication_year":1998,"publication_date":"1998-12-01","ids":{"openalex":"https://openalex.org/W2065568440","doi":"https://doi.org/10.1016/s0306-4379(98)00027-1","mag":"2065568440"},"language":"en","primary_location":{"id":"doi:10.1016/s0306-4379(98)00027-1","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0306-4379(98)00027-1","pdf_url":null,"source":{"id":"https://openalex.org/S193006928","display_name":"Information Systems","issn_l":"0306-4379","issn":["0306-4379","1873-6076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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 Systems","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/A5040580626","display_name":"Chun\u2010Nan Hsu","orcid":"https://orcid.org/0000-0002-5240-4707"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chun-Nan Hsu","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan","Institute of Information Science,Academia Sinica,,Taipei,,Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Institute of Information Science,Academia Sinica,,Taipei,,Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034141547","display_name":"Ming-Tzung Dung","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming-Tzung Dung","raw_affiliation_strings":["Department of Computer Science and Engineering, Arizona State University, Tempe, AZ, USA","Department of Computer Science & Engineering, Arizona State University, Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Department of Computer Science & Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040580626"],"corresponding_institution_ids":["https://openalex.org/I4210098366","https://openalex.org/I84653119"],"apc_list":{"value":2970,"currency":"USD","value_usd":2970},"apc_paid":null,"fwci":26.8463,"has_fulltext":false,"cited_by_count":414,"citation_normalized_percentile":{"value":0.99572317,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"23","issue":"8","first_page":"521","last_page":"538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.949400007724762,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9125999808311462,"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":0.8229089379310608},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.6316419839859009},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5270467400550842},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.4455467462539673},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44074052572250366},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42354440689086914},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.4169695973396301},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4123406708240509},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40685901045799255},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3147392272949219},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09176379442214966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8229089379310608},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.6316419839859009},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5270467400550842},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.4455467462539673},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44074052572250366},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42354440689086914},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.4169695973396301},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4123406708240509},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40685901045799255},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3147392272949219},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09176379442214966},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/s0306-4379(98)00027-1","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0306-4379(98)00027-1","pdf_url":null,"source":{"id":"https://openalex.org/S193006928","display_name":"Information Systems","issn_l":"0306-4379","issn":["0306-4379","1873-6076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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 Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.51.8159","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.51.8159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.iis.sinica.edu.tw/~chunnan/DOWNLOADS/jis2.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life below water","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/14"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1487227972","https://openalex.org/W1531361018","https://openalex.org/W1553019137","https://openalex.org/W1596324102","https://openalex.org/W1965014786","https://openalex.org/W1970406594","https://openalex.org/W1990874659","https://openalex.org/W2026080185","https://openalex.org/W2075476359","https://openalex.org/W2080402044","https://openalex.org/W2083317499","https://openalex.org/W2093476618","https://openalex.org/W2131165428","https://openalex.org/W2141824507","https://openalex.org/W2154836536","https://openalex.org/W2156049581","https://openalex.org/W2183978789","https://openalex.org/W2294792814","https://openalex.org/W2473419855","https://openalex.org/W2912059301","https://openalex.org/W3211952227","https://openalex.org/W4249852273","https://openalex.org/W6629070510","https://openalex.org/W6631751300","https://openalex.org/W6633154970","https://openalex.org/W6642674909","https://openalex.org/W6656961977","https://openalex.org/W6669589398","https://openalex.org/W6671542023","https://openalex.org/W6679496300","https://openalex.org/W6682655823","https://openalex.org/W6683209587","https://openalex.org/W6685940862","https://openalex.org/W6697290312","https://openalex.org/W6720271413"],"related_works":["https://openalex.org/W1495666889","https://openalex.org/W2963140294","https://openalex.org/W2100071482","https://openalex.org/W2729360854","https://openalex.org/W2780890200","https://openalex.org/W2165565716","https://openalex.org/W3088578348","https://openalex.org/W2137912379","https://openalex.org/W4249203355","https://openalex.org/W2124649262"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":19},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":27}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
