{"id":"https://openalex.org/W96326492","doi":"https://doi.org/10.21437/interspeech.2007-434","title":"A semi-supervised learning approach for morpheme segmentation for an Arabic dialect","display_name":"A semi-supervised learning approach for morpheme segmentation for an Arabic dialect","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W96326492","doi":"https://doi.org/10.21437/interspeech.2007-434","mag":"96326492"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-434","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5101870407","display_name":"Mei Yang","orcid":"https://orcid.org/0000-0003-0367-2841"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mei Yang","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101494873","display_name":"Jing Zheng","orcid":"https://orcid.org/0000-0003-2724-8471"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Zheng","raw_affiliation_strings":["SRI, International;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022894728","display_name":"Andreas Kathol","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Kathol","raw_affiliation_strings":["SRI, International;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1501","last_page":"1504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","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"}},{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9865000247955322,"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/morpheme","display_name":"Morpheme","score":0.8222471475601196},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8036786317825317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7413380146026611},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6173878312110901},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5989595055580139},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5927879214286804},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5770199298858643},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5395350456237793},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5191285014152527},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5072728991508484},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.506091296672821},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4823002815246582},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.46820762753486633},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.4430367350578308},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4362199902534485},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4205324351787567},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33518826961517334},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12275543808937073},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0843333899974823}],"concepts":[{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.8222471475601196},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8036786317825317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7413380146026611},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6173878312110901},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5989595055580139},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5927879214286804},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5770199298858643},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5395350456237793},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5191285014152527},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5072728991508484},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.506091296672821},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4823002815246582},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.46820762753486633},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.4430367350578308},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4362199902534485},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4205324351787567},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33518826961517334},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12275543808937073},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0843333899974823},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2007-434","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.123.9195","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.123.9195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ssli.ee.washington.edu/people/yangmei/interspeech07.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W4629839","https://openalex.org/W63733644","https://openalex.org/W147720932","https://openalex.org/W1631260214","https://openalex.org/W2043693083","https://openalex.org/W2119168550","https://openalex.org/W2146574666","https://openalex.org/W2156985047","https://openalex.org/W2160538511","https://openalex.org/W2168576900","https://openalex.org/W2170464899","https://openalex.org/W2608305975"],"related_works":["https://openalex.org/W1532139253","https://openalex.org/W2145230572","https://openalex.org/W2122118939","https://openalex.org/W2166312020","https://openalex.org/W180844028","https://openalex.org/W4401751953","https://openalex.org/W156567445","https://openalex.org/W1989887389","https://openalex.org/W3136989387","https://openalex.org/W2348990643"],"abstract_inverted_index":{"We":[0,18],"present":[1],"a":[2,8,31,52,76,87,114],"semi-supervised":[3],"learning":[4,12],"approach":[5,21,41,55,74,110],"which":[6],"utilizes":[7],"heuristic":[9],"model":[10],"for":[11,15],"morpheme":[13,24,124],"segmentation":[14,25,125],"Arabic":[16,65],"dialects.":[17],"evaluate":[19],"our":[20,40,63,73,109],"by":[22],"applying":[23],"to":[26,45,104],"the":[27,46,82,93,98,105],"training":[28,83],"data":[29],"of":[30,48],"statistical":[32],"machine":[33],"translation":[34],"(SMT)":[35],"system.":[36],"Experiments":[37],"show":[38],"that":[39],"is":[42],"less":[43],"sensitive":[44],"availability":[47],"annotated":[49],"stems":[50],"than":[51],"previous":[53],"rule-based":[54,106],"and":[56,86],"learns":[57],"12":[58],"%":[59,78,89],"more":[60],"segmentations":[61],"on":[62,97],"Iraqi":[64,122],"data.":[66],"When":[67],"applied":[68],"in":[69,81,92,113,117],"an":[70],"SMT":[71],"system,":[72],"yields":[75],"8":[77],"relative":[79,90],"reduction":[80,91],"vocabulary":[84],"size":[85],"0.8":[88],"out-of-vocabulary":[94],"(OOV)":[95],"rate":[96],"test":[99],"set,":[100],"again":[101],"as":[102],"compared":[103],"approach.":[107],"Finally,":[108],"also":[111],"results":[112],"modest":[115],"increase":[116],"BLEU":[118],"scores.":[119],"Index":[120],"Terms:":[121],"Arabic,":[123],"1.":[126]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}