{"id":"https://openalex.org/W2009779948","doi":"https://doi.org/10.1145/1644879.1644883","title":"Morphology-Based Segmentation Combination for Arabic Mention Detection","display_name":"Morphology-Based Segmentation Combination for Arabic Mention Detection","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2009779948","doi":"https://doi.org/10.1145/1644879.1644883","mag":"2009779948"},"language":"en","primary_location":{"id":"doi:10.1145/1644879.1644883","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1644879.1644883","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian Language Information Processing","raw_type":"journal-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/A5109466332","display_name":"Yassine Benajiba","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yassine Benajiba","raw_affiliation_strings":["Center for Computational Learning Systems, Columbia University","Center for Computational Learning Systems, Columbia University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Learning Systems, Columbia University","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Center for Computational Learning Systems, Columbia University#TAB#","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108365460","display_name":"Imed Zitouni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Imed Zitouni","raw_affiliation_strings":["IBM T. J. Watson Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7178,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90716646,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"8","issue":"4","first_page":"1","last_page":"18"},"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":0.9995999932289124,"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/T13629","display_name":"Text Readability and Simplification","score":0.9973000288009644,"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/treebank","display_name":"Treebank","score":0.893174946308136},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8540589809417725},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7230509519577026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.674862265586853},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6585260033607483},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5977658629417419},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5612086653709412},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.5020246505737305},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.1853419542312622},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15641531348228455}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.893174946308136},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8540589809417725},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7230509519577026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.674862265586853},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6585260033607483},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5977658629417419},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5612086653709412},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.5020246505737305},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.1853419542312622},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15641531348228455},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1644879.1644883","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1644879.1644883","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1500614872","https://openalex.org/W1623072288","https://openalex.org/W1654022110","https://openalex.org/W1977830583","https://openalex.org/W1996430422","https://openalex.org/W1997938337","https://openalex.org/W2008830554","https://openalex.org/W2016522586","https://openalex.org/W2022414723","https://openalex.org/W2048978997","https://openalex.org/W2096175520","https://openalex.org/W2097341304","https://openalex.org/W2097927681","https://openalex.org/W2142340904","https://openalex.org/W2144578941","https://openalex.org/W2147880316","https://openalex.org/W2158195707","https://openalex.org/W2160538511","https://openalex.org/W2163306339","https://openalex.org/W2598654328","https://openalex.org/W2796084947","https://openalex.org/W2915429162","https://openalex.org/W3088738244"],"related_works":["https://openalex.org/W2740662036","https://openalex.org/W2574655014","https://openalex.org/W2978383222","https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2058548953","https://openalex.org/W2785359773","https://openalex.org/W2362013696"],"abstract_inverted_index":{"The":[0],"Arabic":[1,9,29,87,114,151,155,183],"language":[2,51],"has":[3,92],"a":[4,60,66,72,173,178],"very":[5,93],"rich/complex":[6],"morphology.":[7],"Each":[8],"word":[10,46],"is":[11,31,42,58,65],"composed":[12],"of":[13,109,136,144,167],"zero":[14,22],"or":[15,23],"more":[16,24,127],"prefixes":[17],",":[18],"one":[19,129],"stem":[20],"and":[21,40,118,146,157,159,185],"suffixes":[25],".":[26],"Consequently,":[27],"the":[28,55,77,97,107,134,165],"data":[30],"sparse":[32],"compared":[33],"to":[34,44,172],"other":[35],"languages":[36],"such":[37],"as":[38],"English,":[39],"it":[41,64],"necessary":[43],"conduct":[45],"segmentation":[47,111,130,148,169],"before":[48],"any":[49],"natural":[50],"processing":[52],"task.":[53],"Therefore,":[54],"word-segmentation":[56],"step":[57,68],"worth":[59],"deeper":[61],"study":[62],"since":[63],"preprocessing":[67],"which":[69],"shall":[70],"have":[71],"significant":[73,180],"impact":[74,108],"on":[75,113],"all":[76],"steps":[78],"coming":[79],"afterward.":[80],"In":[81],"this":[82],"article,":[83],"we":[84,119],"present":[85],"an":[86],"mention":[88,115,138],"detection":[89,116,139],"system":[90],"that":[91,164],"competitive":[94,168],"results":[95],"in":[96],"recent":[98],"Automatic":[99],"Content":[100],"Extraction":[101],"(ACE)":[102],"evaluation":[103],"campaign.":[104],"We":[105,132,162],"investigate":[106],"different":[110,142],"schemes":[112,149],"systems":[117,123],"show":[120,163],"how":[121],"these":[122],"may":[124],"benefit":[125],"from":[126],"than":[128],"scheme.":[131],"report":[133],"performance":[135],"several":[137],"models":[140],"using":[141],"kinds":[143],"possible":[145],"known":[147],"for":[150],"text:":[152],"punctuation":[153],"separation,":[154],"Treebank,":[156],"morphological":[158,186],"character-level":[160],"segmentations.":[161],"combination":[166],"styles":[170],"leads":[171],"better":[174],"performance.":[175],"Results":[176],"indicate":[177],"statistically":[179],"improvement":[181],"when":[182],"Treebank":[184],"segmentations":[187],"are":[188],"combined.":[189]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
