{"id":"https://openalex.org/W3156534109","doi":"https://doi.org/10.1145/3404835.3463102","title":"Gazetteer Enhanced Named Entity Recognition for Code-Mixed Web Queries","display_name":"Gazetteer Enhanced Named Entity Recognition for Code-Mixed Web Queries","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3156534109","doi":"https://doi.org/10.1145/3404835.3463102","mag":"3156534109"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3463102","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5001039604","display_name":"Besnik Fetahu","orcid":"https://orcid.org/0000-0002-3343-7992"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Besnik Fetahu","raw_affiliation_strings":["Amazon.com, Inc., Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com, Inc., Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049221759","display_name":"Anjie Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anjie Fang","raw_affiliation_strings":["Amazon.com, Inc., Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com, Inc., Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024656386","display_name":"Oleg Rokhlenko","orcid":"https://orcid.org/0000-0002-7158-9161"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oleg Rokhlenko","raw_affiliation_strings":["Amazon.com, Inc., Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com, Inc., Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059403175","display_name":"Shervin Malmasi","orcid":"https://orcid.org/0000-0001-6250-5571"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shervin Malmasi","raw_affiliation_strings":["Amazon.com, Inc., Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com, Inc., Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":8.4892,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.98306914,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1677","last_page":"1681"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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/T11719","display_name":"Data Quality and Management","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8857764005661011},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6055330038070679},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.586950421333313},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.5288511514663696},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4872704744338989},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.4686305522918701},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4618607461452484},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4302324652671814},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.363079696893692},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.357097327709198},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.342441201210022}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8857764005661011},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6055330038070679},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.586950421333313},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.5288511514663696},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4872704744338989},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4686305522918701},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4618607461452484},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4302324652671814},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.363079696893692},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.357097327709198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.342441201210022},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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:10.1145/3404835.3463102","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2091950909","https://openalex.org/W2098700435","https://openalex.org/W2150155583","https://openalex.org/W2177726182","https://openalex.org/W2576826140","https://openalex.org/W2594200884","https://openalex.org/W2747329762","https://openalex.org/W2760505947","https://openalex.org/W2767951967","https://openalex.org/W2906848511","https://openalex.org/W2952112859","https://openalex.org/W2963096844","https://openalex.org/W3018024187","https://openalex.org/W3162486530"],"related_works":["https://openalex.org/W2046765700","https://openalex.org/W2780629932","https://openalex.org/W4384345686","https://openalex.org/W3199871245","https://openalex.org/W2357937784","https://openalex.org/W2547618384","https://openalex.org/W4394391052","https://openalex.org/W2145834781","https://openalex.org/W2577782152","https://openalex.org/W262455470"],"abstract_inverted_index":{"Named":[0],"entity":[1],"recognition":[2],"(NER)":[3],"for":[4,61],"Web":[5],"queries":[6,51,156,172],"is":[7],"very":[8,20],"challenging.":[9],"Queries":[10],"often":[11],"do":[12],"not":[13],"consist":[14],"of":[15,39,84,179],"well-formed":[16],"sentences,":[17],"and":[18,66,142,145],"contain":[19],"little":[21],"context,":[22],"with":[23,30,97,128,173],"highly":[24],"ambiguous":[25],"queried":[26],"entities.":[27],"Code-mixed":[28],"queries,":[29,63],"entities":[31,65,144,169],"in":[32,46,72,94,149,157,170],"a":[33,43,91,119,129,182],"different":[34,73,99],"language":[35,109],"than":[36],"the":[37,40,82],"rest":[38],"query,":[41],"pose":[42],"particular":[44],"challenge":[45],"domains":[47],"like":[48],"e-commerce":[49],"(e.g.":[50],"containing":[52],"movie":[53],"or":[54],"product":[55],"names).":[56],"This":[57],"work":[58],"tackles":[59],"NER":[60,86],"code-mixed":[62,85,155,171],"where":[64],"non-entity":[67,146],"query":[68,104,147],"terms":[69,148],"co-exist":[70],"simultaneously":[71,140],"languages.":[74,151],"Our":[75],"contributions":[76],"are":[77],"twofold.":[78],"First,":[79],"to":[80,132,139,167],"address":[81],"lack":[83],"data":[87],"we":[88,106,117],"create":[89],"EMBER,":[90],"large-scale":[92],"dataset":[93],"six":[95],"languages":[96,159],"four":[98],"scripts.":[100],"Based":[101],"on":[102,154],"Bing":[103],"data,":[105],"include":[107],"numerous":[108],"combinations":[110],"that":[111,123,161],"showcase":[112],"real-world":[113],"search":[114],"scenarios.":[115],"Secondly,":[116],"propose":[118],"novel":[120],"gated":[121],"architecture":[122],"enhances":[124],"existing":[125],"multi-lingual":[126,135],"Transformers":[127],"Mixture-of-Experts":[130],"model":[131],"dynamically":[133],"infuse":[134],"gazetteers,":[136],"allowing":[137],"it":[138],"differentiate":[141],"handle":[143],"multiple":[150],"Experimental":[152],"evaluation":[153],"several":[158],"shows":[160],"our":[162],"approach":[163],"efficiently":[164],"utilizes":[165],"gazetteers":[166],"recognize":[168],"an":[174,176],"F1=68%,":[175],"absolute":[177],"improvement":[178],"+31%":[180],"over":[181],"non-gazetteer":[183],"baseline.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":29}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}