{"id":"https://openalex.org/W2102650742","doi":"https://doi.org/10.1145/1277741.1277852","title":"Detecting, categorizing and clustering entity mentions in Chinese text","display_name":"Detecting, categorizing and clustering entity mentions in Chinese text","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2102650742","doi":"https://doi.org/10.1145/1277741.1277852","mag":"2102650742"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277852","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-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/A5100408983","display_name":"Wenjie Li","orcid":"https://orcid.org/0000-0002-7360-8864"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Wenjie Li","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075805272","display_name":"Donglei Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donglei Qian","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016391596","display_name":"Qin Lu","orcid":"https://orcid.org/0000-0002-9092-2476"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qin Lu","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103368914","display_name":"Chunfa Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunfa Yuan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100408983"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":2.8161,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.91359181,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"647","last_page":"654"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9980000257492065,"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":0.8471778631210327},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7516211271286011},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6561448574066162},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6476554870605469},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6209875345230103},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5859841108322144},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5340107083320618},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.4955548048019409},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4932176470756531},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4715542793273926},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.44842439889907837},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.44125139713287354},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36214643716812134},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32851850986480713}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8471778631210327},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7516211271286011},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6561448574066162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6476554870605469},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6209875345230103},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5859841108322144},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5340107083320618},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4955548048019409},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4932176470756531},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4715542793273926},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.44842439889907837},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.44125139713287354},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36214643716812134},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32851850986480713},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1277741.1277852","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W182104056","https://openalex.org/W1484305962","https://openalex.org/W1500614872","https://openalex.org/W1796242380","https://openalex.org/W1967350923","https://openalex.org/W1997938337","https://openalex.org/W2035534443","https://openalex.org/W2072823612","https://openalex.org/W2104619957","https://openalex.org/W2119198250","https://openalex.org/W2123512824","https://openalex.org/W2131340601","https://openalex.org/W2149956050","https://openalex.org/W2164455818","https://openalex.org/W2786686348"],"related_works":["https://openalex.org/W4293471857","https://openalex.org/W2790214503","https://openalex.org/W3144382987","https://openalex.org/W2393940967","https://openalex.org/W2399697877","https://openalex.org/W2250810694","https://openalex.org/W2385598138","https://openalex.org/W2346578824","https://openalex.org/W2366925922","https://openalex.org/W2159591557"],"abstract_inverted_index":{"The":[0,27,139],"work":[1],"presented":[2],"in":[3,78],"this":[4,66],"paper":[5],"is":[6,35],"motivated":[7],"by":[8,118,135],"the":[9,16,24,53,59,75,79,112,150,160],"practical":[10],"need":[11],"for":[12],"content":[13],"extraction,":[14],"and":[15,20,31,47,58,89,100,106,121,131,168,173],"available":[17],"data":[18],"source":[19],"evaluation":[21],"benchmark":[22],"from":[23,52],"ACE":[25,143],"program.":[26],"Chinese":[28,153],"Entity":[29],"Detection":[30],"Recognition":[32],"(EDR)":[33],"task":[34,42],"of":[36,55,61,85,96,129,145,159],"particular":[37],"interest":[38],"to":[39,73,111,165],"us.":[40],"This":[41],"presents":[43],"us":[44],"several":[45],"language-independent":[46],"language-dependent":[48],"challenges,":[49],"e.g.":[50],"rising":[51],"complication":[54],"extraction":[56],"targets":[57],"problem":[60],"word":[62],"segmentation,":[63],"etc.":[64],"In":[65],"paper,":[67],"we":[68],"propose":[69],"a":[70],"novel":[71],"solution":[72],"alleviate":[74],"problems":[76],"special":[77],"task.":[80],"Mention":[81],"detection":[82,167],"takes":[83],"advantages":[84],"machine":[86],"learning":[87],"approaches":[88,164],"character-based":[90],"models.":[91],"It":[92],"manipulates":[93],"different":[94,101],"types":[95],"entities":[97,132],"being":[98],"mentioned":[99],"constitution":[102],"units":[103],"(i.e.":[104],"extents":[105],"heads)":[107],"separately.":[108],"Mentions":[109],"referring":[110],"same":[113],"entity":[114],"are":[115,133,170],"linked":[116],"together":[117],"integrating":[119],"most-specific-first":[120],"closest-first":[122],"rule":[123],"based":[124],"pairwise":[125],"clustering":[126,169],"algorithms.":[127],"Types":[128],"mentions":[130],"determined":[134],"head-driven":[136],"classification":[137],"approaches.":[138],"implemented":[140],"system":[141],"achieves":[142],"value":[144],"66.1":[146],"when":[147],"evaluated":[148],"on":[149],"EDR":[151],"2005":[152],"corpus,":[154],"which":[155],"has":[156],"been":[157],"one":[158],"top-tier":[161],"results.":[162],"Alternative":[163],"mention":[166],"also":[171],"discussed":[172],"analyzed.":[174]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}