{"id":"https://openalex.org/W2165217530","doi":"https://doi.org/10.3115/1220175.1220236","title":"Segment-based hidden Markov models for information extraction","display_name":"Segment-based hidden Markov models for information extraction","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2165217530","doi":"https://doi.org/10.3115/1220175.1220236","mag":"2165217530"},"language":"en","primary_location":{"id":"doi:10.3115/1220175.1220236","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220236","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1220236&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=1220236&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058587755","display_name":"Zhenmei Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhenmei Gu","raw_affiliation_strings":["University of Waterloo, Waterloo, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105530330","display_name":"Nick Cercone","orcid":null},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nick Cercone","raw_affiliation_strings":["Dalhousie University, Halifax, Nova Scotia, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, Nova Scotia, Canada","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.22962068,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"481","last_page":"488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9937000274658203,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9937000274658203,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.992900013923645,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.9183670282363892},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8139423131942749},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7212441563606262},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5900561809539795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5854368209838867},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5602479577064514},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.44849419593811035},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4370821416378021},{"id":"https://openalex.org/keywords/maximum-entropy-markov-model","display_name":"Maximum-entropy Markov model","score":0.41964191198349},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3958514928817749},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.35355091094970703},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.29980263113975525},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21779468655586243},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09708046913146973},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.09545686841011047}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9183670282363892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8139423131942749},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7212441563606262},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5900561809539795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5854368209838867},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5602479577064514},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.44849419593811035},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4370821416378021},{"id":"https://openalex.org/C196956702","wikidata":"https://www.wikidata.org/wiki/Q6795829","display_name":"Maximum-entropy Markov model","level":5,"score":0.41964191198349},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3958514928817749},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.35355091094970703},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.29980263113975525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21779468655586243},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09708046913146973},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.09545686841011047},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1220175.1220236","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220236","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1220236&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.143.9501","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.9501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P06/P06-1061.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1220175.1220236","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220236","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1220236&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2165217530.pdf","grobid_xml":"https://content.openalex.org/works/W2165217530.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1534730506","https://openalex.org/W1934019294","https://openalex.org/W1979960035","https://openalex.org/W1999595522","https://openalex.org/W2125838338","https://openalex.org/W2137650255","https://openalex.org/W2139193890","https://openalex.org/W2149316185","https://openalex.org/W2163918411","https://openalex.org/W4253573210","https://openalex.org/W4302585900"],"related_works":["https://openalex.org/W2134386692","https://openalex.org/W2379938888","https://openalex.org/W1510894296","https://openalex.org/W2116722627","https://openalex.org/W1977445474","https://openalex.org/W4233405330","https://openalex.org/W2032015827","https://openalex.org/W2194396582","https://openalex.org/W2082284720","https://openalex.org/W2566202039"],"abstract_inverted_index":{"Hidden":[0],"Markov":[1],"models":[2,7],"(HMMs)":[3],"are":[4],"powerful":[5],"statistical":[6],"that":[8,47,110],"have":[9],"found":[10],"successful":[11],"applications":[12],"in":[13,42,44,68],"Information":[14],"Extraction":[15],"(IE).":[16],"In":[17,86],"current":[18],"approaches":[19],"to":[20,23,29,58,61,88,98,101],"applying":[21],"HMMs":[22,60,100],"IE,":[24],"an":[25,83],"HMM":[26,114,134],"is":[27,52],"used":[28],"model":[30,62,102],"text":[31,63],"at":[32,64],"the":[33,45,65,70,111],"document":[34,133],"level.":[35],"This":[36],"modelling":[37],"might":[38],"cause":[39],"undesired":[40],"redundancy":[41],"extraction":[43,71,84,122,129],"sense":[46],"more":[48],"than":[49,131],"one":[50],"filler":[51],"identified":[53],"and":[54,103],"extracted.":[55],"We":[56],"propose":[57],"use":[59,99],"segment":[66,78,113],"level,":[67],"which":[69],"process":[72],"consists":[73],"of":[74],"two":[75],"steps:":[76],"a":[77,96],"retrieval":[79],"step":[80],"followed":[81],"by":[82],"step.":[85],"order":[87],"retrieve":[89,104],"extraction-relevant":[90],"segments":[91],"from":[92],"documents,":[93],"we":[94],"introduce":[95],"method":[97],"segments.":[105],"Our":[106],"experimental":[107],"results":[108],"show":[109],"resulting":[112],"IE":[115,135],"system":[116],"not":[117],"only":[118],"achieves":[119],"near":[120],"zero":[121],"redundancy,":[123],"but":[124],"also":[125],"has":[126],"better":[127],"overall":[128],"performance":[130],"traditional":[132],"systems.":[136]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}