{"id":"https://openalex.org/W2554497695","doi":"https://doi.org/10.1109/ialp.2016.7875939","title":"The effect of shallow segmentation on English-Tigrinya statistical machine translation","display_name":"The effect of shallow segmentation on English-Tigrinya statistical machine translation","publication_year":2016,"publication_date":"2016-11-01","ids":{"openalex":"https://openalex.org/W2554497695","doi":"https://doi.org/10.1109/ialp.2016.7875939","mag":"2554497695"},"language":"en","primary_location":{"id":"doi:10.1109/ialp.2016.7875939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2016.7875939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Asian Language Processing (IALP)","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/A5008064221","display_name":"Yemane Tedla","orcid":null},"institutions":[{"id":"https://openalex.org/I85922643","display_name":"Nagaoka University of Technology","ror":"https://ror.org/00ys1hz88","country_code":"JP","type":"education","lineage":["https://openalex.org/I85922643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yemane Tedla","raw_affiliation_strings":["Nagaoka University of Technology, Natural Language Processing Lab, Nagaoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagaoka University of Technology, Natural Language Processing Lab, Nagaoka, Japan","institution_ids":["https://openalex.org/I85922643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109500211","display_name":"Kazuhide Yamamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I85922643","display_name":"Nagaoka University of Technology","ror":"https://ror.org/00ys1hz88","country_code":"JP","type":"education","lineage":["https://openalex.org/I85922643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhide Yamamoto","raw_affiliation_strings":["Nagaoka University of Technology, Natural Language Processing Lab, Nagaoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagaoka University of Technology, Natural Language Processing Lab, Nagaoka, Japan","institution_ids":["https://openalex.org/I85922643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I85922643"],"apc_list":null,"apc_paid":null,"fwci":0.1941,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.51148033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"33","issue":null,"first_page":"79","last_page":"82"},"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":0.9969000220298767,"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":0.9787999987602234,"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":0.8185279369354248},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.8157691359519958},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7732312679290771},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7364818453788757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6893223524093628},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6630896925926208},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.616984486579895},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5138028264045715},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4776383936405182},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4657595455646515},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4148206114768982},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36308079957962036},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18773153424263}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185279369354248},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8157691359519958},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7732312679290771},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7364818453788757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6893223524093628},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6630896925926208},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.616984486579895},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5138028264045715},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4776383936405182},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4657595455646515},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4148206114768982},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36308079957962036},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18773153424263},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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:10.1109/ialp.2016.7875939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2016.7875939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1588612820","https://openalex.org/W1981287915","https://openalex.org/W2124807415","https://openalex.org/W2134285054","https://openalex.org/W2135161317","https://openalex.org/W2152277656","https://openalex.org/W2343202152","https://openalex.org/W2397861673","https://openalex.org/W2403096031","https://openalex.org/W6704603883"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2921174581","https://openalex.org/W2084531783","https://openalex.org/W2020757772"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"initial":[3],"research":[4],"on":[5,95],"English-to-Tigrinya":[6],"statistical":[7],"machine":[8],"translation":[9,83,96],"(SMT).":[10],"Tigrinya":[11,50,73],"is":[12,28],"a":[13,53,105],"highly":[14],"inflected":[15],"Semitic":[16],"language":[17,38,61],"spoken":[18],"in":[19,72],"Eritrea":[20],"and":[21,37,63,86],"Ethiopia.":[22],"Translation":[23],"involving":[24],"morphologically":[25],"complex":[26],"languages":[27],"challenged":[29],"by":[30,78],"factors":[31],"including":[32],"data":[33],"sparseness,":[34],"word":[35],"alignment":[36],"model.":[39],"We":[40,80],"try":[41],"to":[42,89],"address":[43],"these":[44],"problems":[45],"through":[46],"morphological":[47],"segmentation":[48,94],"of":[49,55,59,93],"words.":[51],"As":[52],"result":[54],"segmentation,":[56],"the":[57,60,70,91],"size":[58],"model":[62],"its":[64],"perplexity":[65],"were":[66],"greatly":[67],"reduced.":[68],"Furthermore,":[69],"increase":[71],"tokens":[74],"decreased":[75],"out-of-vocabulary":[76],"ratio":[77],"46%.":[79],"analysed":[81],"phrase-based":[82],"with":[84],"unsegmented":[85],"segmented":[87],"corpus":[88],"investigate":[90],"effect":[92],"quality.":[97],"Preliminary":[98],"results":[99],"demonstrate":[100],"promising":[101],"performance":[102],"improvement":[103],"from":[104],"relatively":[106],"small":[107],"parallel":[108],"corpus.":[109]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}