{"id":"https://openalex.org/W2251924162","doi":"https://doi.org/10.3115/v1/w14-4006","title":"Reducing the Impact of Data Sparsity in Statistical Machine Translation","display_name":"Reducing the Impact of Data Sparsity in Statistical Machine Translation","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251924162","doi":"https://doi.org/10.3115/v1/w14-4006","mag":"2251924162"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-4006","is_oa":true,"landing_page_url":"http://doi.org/10.3115/v1/w14-4006","pdf_url":"https://doi.org/10.3115/v1/w14-4006","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3115/v1/w14-4006","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017498707","display_name":"Karan Singla","orcid":"https://orcid.org/0000-0002-2735-8673"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karan Singla","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077915577","display_name":"Kunal Sachdeva","orcid":"https://orcid.org/0000-0002-7739-0073"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kunal Sachdeva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111475783","display_name":"Srinivas Bangalore","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srinivas Bangalore","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047549045","display_name":"Dipti Misra Sharma","orcid":"https://orcid.org/0009-0000-6979-3609"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dipti Misra Sharma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077871642","display_name":"Diksha Yadav","orcid":"https://orcid.org/0000-0002-2027-7766"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diksha Yadav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"56"},"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":0.9997000098228455,"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":0.9850999712944031,"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":0.8812082409858704},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.843297004699707},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.7848016619682312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6321213841438293},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6124253273010254},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6028975248336792},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.48184049129486084},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44284379482269287},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3601417541503906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8812082409858704},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.843297004699707},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.7848016619682312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6321213841438293},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6124253273010254},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6028975248336792},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.48184049129486084},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44284379482269287},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3601417541503906},{"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/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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/w14-4006","is_oa":true,"landing_page_url":"http://doi.org/10.3115/v1/w14-4006","pdf_url":"https://doi.org/10.3115/v1/w14-4006","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.675.9450","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.675.9450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology/W/W14/W14-4006.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-4006","is_oa":true,"landing_page_url":"http://doi.org/10.3115/v1/w14-4006","pdf_url":"https://doi.org/10.3115/v1/w14-4006","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W114288850","https://openalex.org/W179875071","https://openalex.org/W1257140033","https://openalex.org/W1631260214","https://openalex.org/W1934041838","https://openalex.org/W1973923101","https://openalex.org/W2020015729","https://openalex.org/W2026149468","https://openalex.org/W2058695628","https://openalex.org/W2097606805","https://openalex.org/W2107878631","https://openalex.org/W2113788796","https://openalex.org/W2116337133","https://openalex.org/W2122609803","https://openalex.org/W2153653739","https://openalex.org/W2159556392","https://openalex.org/W2162245945","https://openalex.org/W2170204377","https://openalex.org/W2251507105","https://openalex.org/W2251955011","https://openalex.org/W2405047074","https://openalex.org/W2407892396","https://openalex.org/W3098204167","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2919826171","https://openalex.org/W2786253471","https://openalex.org/W4394652048","https://openalex.org/W2072889429","https://openalex.org/W3175595715","https://openalex.org/W187239208","https://openalex.org/W38167433","https://openalex.org/W78710524"],"abstract_inverted_index":{"Morphologically":[0],"rich":[1],"languages":[2],"generally":[3],"require":[4],"large":[5,29,48],"amounts":[6],"of":[7,31,47,56,77,86],"parallel":[8,32,49],"data":[9],"to":[10,27,83],"adequately":[11],"estimate":[12],"parameters":[13],"in":[14,59],"a":[15],"statis-tical":[16],"Machine":[17],"Translation(SMT)":[18],"system.":[19],"However,":[20],"it":[21],"is":[22],"time":[23],"consuming":[24],"and":[25,71],"expen-sive":[26],"create":[28],"collections":[30],"data.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37,52,73],"explore":[38,74],"two":[39],"strate-gies":[40],"for":[41],"circumventing":[42],"sparsity":[43,85],"caused":[44],"by":[45],"lack":[46],"corpora.":[50],"First,":[51],"ex-plore":[53],"the":[54,75],"use":[55,76],"distributed":[57],"representations":[58],"an":[60],"Recurrent":[61],"Neural":[62],"Network":[63],"based":[64],"lan-guage":[65],"model":[66],"with":[67],"different":[68],"morphological":[69],"features":[70],"second,":[72],"lexical":[78],"resources":[79],"such":[80],"as":[81],"WordNet":[82],"over-come":[84],"content":[87],"words.":[88],"1":[89]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
