{"id":"https://openalex.org/W2059044879","doi":"https://doi.org/10.3115/1119250.1119277","title":"Chinese word segmentation in MSR-NLP","display_name":"Chinese word segmentation in MSR-NLP","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2059044879","doi":"https://doi.org/10.3115/1119250.1119277","mag":"2059044879"},"language":"en","primary_location":{"id":"doi:10.3115/1119250.1119277","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119277","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119277","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119277","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112730666","display_name":"Andi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andi Wu","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5112730666"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":4.6796,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.94800321,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"17","issue":null,"first_page":"172","last_page":"175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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":0.9678999781608582,"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/parsing","display_name":"Parsing","score":0.843048095703125},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7618374228477478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7497528791427612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7445923089981079},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7272233963012695},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6008145213127136},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5771595239639282},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5342444777488708},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5160355567932129},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40720611810684204},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38847190141677856},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17294391989707947}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.843048095703125},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7618374228477478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7497528791427612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7445923089981079},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7272233963012695},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6008145213127136},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5771595239639282},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5342444777488708},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5160355567932129},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40720611810684204},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38847190141677856},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17294391989707947},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1119250.1119277","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119277","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119277","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:10.1.1.81.9023","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.81.9023","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/pdfs/Wus.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1119250.1119277","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119277","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119277","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":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2059044879.pdf","grobid_xml":"https://content.openalex.org/works/W2059044879.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W1992863499","https://openalex.org/W2036701977","https://openalex.org/W2098594428","https://openalex.org/W2125641218"],"related_works":["https://openalex.org/W2095908250","https://openalex.org/W2393940967","https://openalex.org/W2159591557","https://openalex.org/W2385598138","https://openalex.org/W2346578824","https://openalex.org/W2366925922","https://openalex.org/W2115592387","https://openalex.org/W2905950556","https://openalex.org/W2112534334","https://openalex.org/W120168696"],"abstract_inverted_index":{"Word":[0],"segmentation":[1,31,48,67],"in":[2,62,84],"MSR-NLP":[3],"is":[4,32],"an":[5],"integral":[6],"part":[7],"of":[8,37,54,57,65,88,95],"a":[9,55],"sentence":[10],"analyzer":[11],"which":[12],"includes":[13],"basic":[14],"segmentation,":[15],"derivational":[16],"morphology,":[17],"named":[18],"entity":[19],"recognition,":[20],"new":[21],"word":[22,24],"identification,":[23],"lattice":[25],"pruning":[26],"and":[27,73,76,81],"parsing.":[28],"The":[29,40,59],"final":[30],"produced":[33],"from":[34],"the":[35,51,66,89,96,100],"leaves":[36],"parse":[38],"trees.":[39],"output":[41],"can":[42],"be":[43],"customized":[44],"to":[45,99],"meet":[46],"different":[47],"standards":[49],"through":[50],"value":[52],"combinations":[53],"set":[56],"parameters.":[58],"system":[60,97],"participated":[61],"four":[63],"tracks":[64],"bakeoff":[68],"--":[69],"PK-open,":[70],"PK-close,":[71],"CTB-open":[72],"CTB-closed":[74],"-":[75],"ranked":[77],"#1,":[78],"#2,":[79],"#2":[80],"#3":[82],"respectively":[83],"those":[85],"tracks.":[86],"Analysis":[87],"results":[90],"shows":[91],"that":[92],"each":[93],"component":[94],"contributed":[98],"scores.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}