{"id":"https://openalex.org/W2163353449","doi":null,"title":"Language-independent compound splitting with morphological operations","display_name":"Language-independent compound splitting with morphological operations","publication_year":2011,"publication_date":"2011-06-19","ids":{"openalex":"https://openalex.org/W2163353449","mag":"2163353449"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.207.5321","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.5321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology-new/P/P11/P11-1140.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5008084569","display_name":"Klaus Macherey","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Klaus Macherey","raw_affiliation_strings":["Google, Inc, Mountain View, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc, Mountain View, CA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101597225","display_name":"Andrew M. Dai","orcid":"https://orcid.org/0009-0007-9200-8577","observed_orcids":["https://orcid.org/0009-0007-9200-8577"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew M. Dai","raw_affiliation_strings":["University of Edinburgh, Edinburgh, UK"],"raw_orcid":"https://orcid.org/0009-0007-9200-8577","affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057541969","display_name":"David Talbot","orcid":"https://orcid.org/0000-0002-9675-2703","observed_orcids":["https://orcid.org/0000-0002-9675-2703"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Talbot","raw_affiliation_strings":["Google, Inc, Mountain View, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc, Mountain View, CA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078560039","display_name":"Ashok C. Popat","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashok C. Popat","raw_affiliation_strings":["Google, Inc, Mountain View, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc, Mountain View, CA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046457818","display_name":"Franz Josef Och","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franz Josef Och","raw_affiliation_strings":["Google, Inc, Mountain View, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc, Mountain View, CA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.5149,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.96477615,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1395","last_page":"1404"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T12353","display_name":"Lexicography and Language Studies","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/compound-splitting","display_name":"compound splitting","score":0.890999972820282},{"id":"https://openalex.org/keywords/decompounding","display_name":"decompounding","score":0.9459999799728394},{"id":"https://openalex.org/keywords/morphological-operations","display_name":"morphological operations","score":0.765999972820282},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.843999981880188},{"id":"https://openalex.org/keywords/bilingual-corpus","display_name":"bilingual corpus","score":0.753000020980835},{"id":"https://openalex.org/keywords/monolingual-corpora","display_name":"monolingual corpora","score":0.9089999794960022}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7762926816940308},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6717071533203125},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6474271416664124},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.62726891040802},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6240834593772888},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6140891313552856},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6050451993942261},{"id":"https://openalex.org/C2674912","wikidata":"https://www.wikidata.org/wiki/Q245423","display_name":"Compound","level":2,"score":0.5485835075378418},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5134819149971008},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.46204161643981934},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2023506760597229},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12135821580886841},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08832433819770813},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.207.5321","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.5321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology-new/P/P11/P11-1140.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.319","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/37093.pdf","raw_type":"text"},{"id":"mag:2163353449","doi":null,"is_oa":false,"landing_page_url":"http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/37093.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Meeting of the Association for Computational Linguistics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1531522183","https://openalex.org/W2016522586","https://openalex.org/W2016856586","https://openalex.org/W2101105183","https://openalex.org/W2124807415","https://openalex.org/W2134913565","https://openalex.org/W2164766438","https://openalex.org/W2397601298"],"related_works":["https://openalex.org/W2463932830","https://openalex.org/W2016856586","https://openalex.org/W2626159181","https://openalex.org/W2135413937","https://openalex.org/W1815552937","https://openalex.org/W2155539936","https://openalex.org/W2940356711","https://openalex.org/W2397601298","https://openalex.org/W2080012968","https://openalex.org/W1633069723"],"abstract_inverted_index":{"Translating":[0],"compounds":[1,11,66],"is":[2],"an":[3],"important":[4],"problem":[5],"in":[6],"machine":[7,111],"translation.":[8],"Since":[9],"many":[10],"have":[12,28],"not":[13],"been":[14,30],"observed":[15],"during":[16],"training,":[17],"they":[18,39],"pose":[19],"a":[20,33,50,74,85,110],"challenge":[21],"for":[22,118],"translation":[23,112],"systems.":[24],"Previous":[25],"decompounding":[26],"methods":[27],"often":[29],"restricted":[31],"to":[32,55,64,77,83,95,121],"small":[34],"set":[35,100],"of":[36,101,125],"languages":[37,120],"as":[38],"cannot":[40],"deal":[41],"with":[42],"more":[43],"complex":[44],"compound":[45,58,69,86,102],"forming":[46],"processes.":[47],"We":[48,105],"present":[49],"novel":[51],"and":[52,60,97,114],"unsupervised":[53],"method":[54,72,108],"learn":[56,78,96],"the":[57,79,99,123,126],"parts":[59],"morphological":[61,80],"operations":[62,81],"needed":[63],"split":[65,84],"into":[67,87],"their":[68],"parts.":[70,89],"The":[71],"uses":[73],"bilingual":[75],"corpus":[76],"required":[82],"its":[88],"Furthermore,":[90],"monolingual":[91],"corpora":[92],"are":[93],"used":[94],"filter":[98],"part":[103],"candidates.":[104],"evaluate":[106],"our":[107],"within":[109],"task":[113],"show":[115,122],"significant":[116],"improvements":[117],"various":[119],"versatility":[124],"approach.":[127],"1":[128]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":7}],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2016-06-24T00:00:00"}
