{"id":"https://openalex.org/W1977830583","doi":"https://doi.org/10.3115/1621787.1621800","title":"The impact of morphological stemming on Arabic mention detection and coreference resolution","display_name":"The impact of morphological stemming on Arabic mention detection and coreference resolution","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W1977830583","doi":"https://doi.org/10.3115/1621787.1621800","mag":"1977830583"},"language":"en","primary_location":{"id":"doi:10.3115/1621787.1621800","doi":"https://doi.org/10.3115/1621787.1621800","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1621787.1621800","pdf_url":"https://dl.acm.org/doi/pdf/10.5555/1621787.1621800","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages - Semitic '05","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.5555/1621787.1621800","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108365460","display_name":"Imed Zitouni","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Imed Zitouni","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109945273","display_name":"Jeff Sorensen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeff Sorensen","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111895886","display_name":"Xiaoqiang Luo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoqiang Luo","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113515054","display_name":"Radu Florian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Radu Florian","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9021,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.86548003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"63"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9833999872207642,"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":0.9833999872207642,"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":0.01510000042617321,"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/T12031","display_name":"Speech and dialogue systems","score":0.00019999999494757503,"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/arabic","display_name":"Arabic language","score":0.5649999976158142},{"id":"https://openalex.org/keywords/coreference-resolution","display_name":"coreference resolution","score":0.9980000257492065},{"id":"https://openalex.org/keywords/maximum-entropy-model","display_name":"maximum entropy model","score":0.703000009059906},{"id":"https://openalex.org/keywords/agglutinative-languages","display_name":"agglutinative languages","score":0.7059999704360962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8120256662368774},{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.6855593919754028},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6573225259780884},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6485085487365723},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6074762344360352},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.5744987726211548},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.528488278388977},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5133232474327087},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.48586055636405945},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4582807421684265},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3246394693851471},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.22877678275108337},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.15711939334869385},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13705116510391235},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10954740643501282},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1621787.1621800","doi":"https://doi.org/10.3115/1621787.1621800","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1621787.1621800","pdf_url":"https://dl.acm.org/doi/pdf/10.5555/1621787.1621800","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages - Semitic '05","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.59.9121","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.9121","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/W/W05/W05-0709.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1621787.1621800","doi":"https://doi.org/10.3115/1621787.1621800","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1621787.1621800","pdf_url":"https://dl.acm.org/doi/pdf/10.5555/1621787.1621800","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages - Semitic '05","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1977830583.pdf","grobid_xml":"https://content.openalex.org/works/W1977830583.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W88705112","https://openalex.org/W190403182","https://openalex.org/W1500614872","https://openalex.org/W1505083828","https://openalex.org/W1558333962","https://openalex.org/W1972583365","https://openalex.org/W1982982698","https://openalex.org/W1984972187","https://openalex.org/W2036234367","https://openalex.org/W2078499449","https://openalex.org/W2096175520","https://openalex.org/W2097341304","https://openalex.org/W2131340601","https://openalex.org/W2149956050","https://openalex.org/W2155903443","https://openalex.org/W2163918411","https://openalex.org/W2164455818","https://openalex.org/W2953365284"],"related_works":["https://openalex.org/W1774652710","https://openalex.org/W2009779948","https://openalex.org/W2147895967","https://openalex.org/W56096989","https://openalex.org/W7099971265","https://openalex.org/W7095650058","https://openalex.org/W2251221175","https://openalex.org/W1500614872","https://openalex.org/W2137494357","https://openalex.org/W2613292158"],"abstract_inverted_index":{"Arabic":[0],"presents":[1,20],"an":[2,21,70],"interesting":[3],"challenge":[4],"to":[5],"natural":[6],"language":[7],"processing,":[8],"being":[9],"a":[10,41,49,65,86,118],"highly":[11],"inflected":[12],"and":[13,28,53,69],"agglutinative":[14],"language.":[15],"In":[16],"particular,":[17],"this":[18],"paper":[19],"in-depth":[22],"investigation":[23],"of":[24,90,104],"the":[25,57,80,91,102,105,122],"entity":[26,71],"detection":[27,67],"recognition":[29,72],"(EDR)":[30],"task":[31],"for":[32,44],"Arabic.":[33],"We":[34],"start":[35],"by":[36,47,108],"highlighting":[37],"why":[38],"segmentation":[39],"is":[40],"necessary":[42],"prerequisite":[43],"EDR,":[45],"continue":[46],"presenting":[48],"finite-state":[50],"statistical":[51],"segmenter,":[52],"then":[54],"examine":[55],"how":[56],"resulting":[58],"segments":[59],"can":[60,99],"be":[61],"better":[62],"included":[63],"into":[64],"mention":[66],"system":[68,107,114],"system;":[73],"both":[74],"systems":[75],"are":[76],"statistical,":[77],"build":[78],"around":[79],"maximum":[81],"entropy":[82],"principle.":[83],"Experiments":[84],"on":[85],"clearly":[87],"stated":[88],"partition":[89],"ACE":[92,123],"2004":[93,124],"data":[94],"show":[95],"that":[96],"stem-based":[97],"features":[98],"significantly":[100],"improve":[101],"performance":[103,120],"EDT":[106],"2":[109],"absolute":[110],"F-measure":[111],"points.":[112],"The":[113],"presented":[115],"here":[116],"had":[117],"competitive":[119],"in":[121],"evaluation.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}