{"id":"https://openalex.org/W2963338481","doi":"https://doi.org/10.18653/v1/p16-2025","title":"Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Learning","display_name":"Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Learning","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2963338481","doi":"https://doi.org/10.18653/v1/p16-2025","mag":"2963338481"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p16-2025","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-2025","pdf_url":"https://aclanthology.org/P16-2025.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/P16-2025.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030248499","display_name":"Nanyun Peng","orcid":"https://orcid.org/0000-0002-8509-6595"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nanyun Peng","raw_affiliation_strings":["Human Language Technology Center of Excellence Center for Language and Speech Processing Johns Hopkins University, Baltimore, MD, 21218"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence Center for Language and Speech Processing Johns Hopkins University, Baltimore, MD, 21218","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024437840","display_name":"Mark Dredze","orcid":"https://orcid.org/0000-0002-0422-2474"},"institutions":[{"id":"https://openalex.org/I1299907687","display_name":"Bloomberg (United States)","ror":"https://ror.org/02rdpzb15","country_code":"US","type":"company","lineage":["https://openalex.org/I1299907687"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Dredze","raw_affiliation_strings":["Bloomberg LP, New York, NY 10022","Human Language Technology Center of Excellence Center for Language and Speech Processing Johns Hopkins University, Baltimore, MD, 21218"],"affiliations":[{"raw_affiliation_string":"Bloomberg LP, New York, NY 10022","institution_ids":["https://openalex.org/I1299907687"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence Center for Language and Speech Processing Johns Hopkins University, Baltimore, MD, 21218","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030248499"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":26.5656,"has_fulltext":true,"cited_by_count":226,"citation_normalized_percentile":{"value":0.99542487,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"149","last_page":"155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T11550","display_name":"Text and Document Classification Technologies","score":0.9872999787330627,"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":0.791000485420227},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7484469413757324},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6432310342788696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6381363272666931},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6329865455627441},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.521955668926239},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5137602090835571},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.49985790252685547},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43426939845085144},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3219798505306244},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2565050721168518},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19809111952781677},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.061459243297576904}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791000485420227},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7484469413757324},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6432310342788696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6381363272666931},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6329865455627441},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.521955668926239},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5137602090835571},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.49985790252685547},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43426939845085144},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3219798505306244},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2565050721168518},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19809111952781677},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.061459243297576904},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p16-2025","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-2025","pdf_url":"https://aclanthology.org/P16-2025.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p16-2025","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-2025","pdf_url":"https://aclanthology.org/P16-2025.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963338481.pdf","grobid_xml":"https://content.openalex.org/works/W2963338481.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1541691357","https://openalex.org/W1570587036","https://openalex.org/W1940872118","https://openalex.org/W2020278455","https://openalex.org/W2046240631","https://openalex.org/W2100581574","https://openalex.org/W2117130368","https://openalex.org/W2119759918","https://openalex.org/W2130903752","https://openalex.org/W2138627627","https://openalex.org/W2140016149","https://openalex.org/W2141099517","https://openalex.org/W2145111356","https://openalex.org/W2151048449","https://openalex.org/W2153579005","https://openalex.org/W2153848201","https://openalex.org/W2158139315","https://openalex.org/W2245959303","https://openalex.org/W2250387831","https://openalex.org/W2250709962","https://openalex.org/W2250739653","https://openalex.org/W2251276420","https://openalex.org/W2251380531","https://openalex.org/W2251567709","https://openalex.org/W2251811146","https://openalex.org/W2294546627","https://openalex.org/W2296283641","https://openalex.org/W2308486447","https://openalex.org/W2399697877","https://openalex.org/W2400932086","https://openalex.org/W2785349534","https://openalex.org/W2913340405","https://openalex.org/W2962755455","https://openalex.org/W2962902328","https://openalex.org/W3088186095","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2790214503","https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W3144382987","https://openalex.org/W4293471857","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2393940967","https://openalex.org/W2399697877","https://openalex.org/W45206245"],"abstract_inverted_index":{"Named":[0],"entity":[1],"recognition,":[2],"and":[3,112],"other":[4],"information":[5,65],"extraction":[6],"tasks,":[7],"frequently":[8],"use":[9,75],"linguistic":[10],"features":[11,40,51],"such":[12],"as":[13,50],"part":[14],"of":[15],"speech":[16],"tags":[17,49],"or":[18],"chunkings.":[19],"For":[20],"languages":[21],"where":[22],"word":[23,31,47,72,83,113],"boundaries":[24,61],"are":[25,52],"not":[26],"readily":[27],"identified":[28],"in":[29,58,100],"text,":[30],"segmentation":[32,73,114],"is":[33],"a":[34],"key":[35],"first":[36],"step":[37],"to":[38,78],"generating":[39],"for":[41,66,81,102],"an":[42,67,94,116],"NER":[43,68,95,101,111],"system.":[44,69],"While":[45],"using":[46],"boundary":[48],"helpful,":[53],"the":[54],"signals":[55],"that":[56,87],"aid":[57],"identifying":[59],"these":[60,88],"may":[62],"provide":[63],"richer":[64],"New":[70],"state-of-the-art":[71],"systems":[74],"neural":[76],"models":[77],"learn":[79],"representations":[80],"predicting":[82],"boundaries.":[84],"We":[85],"show":[86],"same":[89],"representations,":[90],"jointly":[91,109],"trained":[92],"with":[93,115],"system,":[96],"yield":[97],"significant":[98],"improvements":[99],"Chinese":[103],"social":[104],"media.":[105],"In":[106],"our":[107],"experiments,":[108],"training":[110],"LSTM-CRF":[117],"model":[118],"yields":[119],"nearly":[120],"5%":[121],"absolute":[122],"improvement":[123],"over":[124],"previously":[125],"published":[126],"results.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":33},{"year":2022,"cited_by_count":33},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":38},{"year":2019,"cited_by_count":34},{"year":2018,"cited_by_count":18},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}