{"id":"https://openalex.org/W1979145089","doi":"https://doi.org/10.3115/1119250.1119278","title":"Chinese word segmentation as LMR tagging","display_name":"Chinese word segmentation as LMR tagging","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W1979145089","doi":"https://doi.org/10.3115/1119250.1119278","mag":"1979145089"},"language":"en","primary_location":{"id":"doi:10.3115/1119250.1119278","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119278","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1119278&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second SIGHAN workshop on Chinese language processing -","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=1119278&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036715761","display_name":"Nianwen Xue","orcid":"https://orcid.org/0000-0002-4364-3618"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nianwen Xue","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA","Univ. of Pennsylvania, Philadelphia, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Univ. of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101706257","display_name":"Libin Shen","orcid":"https://orcid.org/0000-0002-7967-0538"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Libin Shen","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA","Univ. of Pennsylvania, Philadelphia, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Univ. of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":158,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":null,"first_page":"176","last_page":"179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9968000054359436,"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":0.7132430076599121},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.6956444382667542},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6857357025146484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6670116782188416},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6505914926528931},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6362476348876953},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6143919825553894},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5479230880737305},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.46110257506370544},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4590439200401306},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.43483978509902954},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4230485260486603},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3551478385925293},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33542823791503906},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.1779855191707611},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15252766013145447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7132430076599121},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.6956444382667542},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6857357025146484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6670116782188416},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6505914926528931},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6362476348876953},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6143919825553894},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5479230880737305},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.46110257506370544},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4590439200401306},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.43483978509902954},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4230485260486603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3551478385925293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33542823791503906},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.1779855191707611},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15252766013145447},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1119250.1119278","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119278","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1119278&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second SIGHAN workshop on Chinese language processing -","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.10.4172","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.4172","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/acl2003/sighan/ps/XueShen.ps","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1119250.1119278","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119278","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1119278&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second SIGHAN workshop on Chinese language processing -","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1979145089.pdf","grobid_xml":"https://content.openalex.org/works/W1979145089.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1558333962","https://openalex.org/W1773803948","https://openalex.org/W2085606725","https://openalex.org/W2098594428","https://openalex.org/W2101857472","https://openalex.org/W2117400858","https://openalex.org/W2118925939","https://openalex.org/W2130636661","https://openalex.org/W2147880316","https://openalex.org/W2163377725","https://openalex.org/W3145501851"],"related_works":["https://openalex.org/W2032184408","https://openalex.org/W2171752604","https://openalex.org/W2363447991","https://openalex.org/W2128096361","https://openalex.org/W2043320108","https://openalex.org/W180844028","https://openalex.org/W2275441552","https://openalex.org/W3143974354","https://openalex.org/W2349070910","https://openalex.org/W2369094010"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,27],"present":[4],"Chinese":[5],"word":[6],"segmentation":[7],"algorithms":[8],"based":[9],"on":[10,56],"the":[11,21,34,37,43,57,62],"so-called":[12],"LMR":[13,16,39],"tagging.":[14],"Our":[15,48],"taggers":[17,40],"are":[18],"implemented":[19],"with":[20],"Maximum":[22],"Entropy":[23],"Markov":[24],"Model":[25],"and":[26,54,61],"then":[28],"use":[29],"Transformation-Based":[30],"Learning":[31],"to":[32],"combine":[33],"results":[35],"of":[36,52],"two":[38],"that":[41],"scan":[42],"input":[44],"in":[45],"opposite":[46],"directions.":[47],"system":[49],"achieves":[50],"F-scores":[51],"95.9%":[53],"91.6%":[55],"Academia":[58],"Sinica":[59],"corpus":[60,67],"Hong":[63],"Kong":[64],"City":[65],"University":[66],"respectively.":[68]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}