{"id":"https://openalex.org/W2250332179","doi":"https://doi.org/10.3115/v1/e14-1061","title":"How to Produce Unseen Teddy Bears: Improved Morphological Processing of Compounds in SMT","display_name":"How to Produce Unseen Teddy Bears: Improved Morphological Processing of Compounds in SMT","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2250332179","doi":"https://doi.org/10.3115/v1/e14-1061","mag":"2250332179"},"language":"en","primary_location":{"id":"doi:10.3115/v1/e14-1061","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-1061","pdf_url":"https://aclanthology.org/E14-1061.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/E14-1061.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086079434","display_name":"Fabienne Cap","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fabienne Cap","raw_affiliation_strings":["CIS, University of Munich"],"affiliations":[{"raw_affiliation_string":"CIS, University of Munich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101957153","display_name":"Alexander Fraser","orcid":"https://orcid.org/0000-0003-4891-682X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Fraser","raw_affiliation_strings":["CIS, University of Munich"],"affiliations":[{"raw_affiliation_string":"CIS, University of Munich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028822761","display_name":"Marion Weller","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marion Weller","raw_affiliation_strings":["IMS, University of Stuttgart"],"affiliations":[{"raw_affiliation_string":"IMS, University of Stuttgart","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048408884","display_name":"Aoife Cahill","orcid":null},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aoife Cahill","raw_affiliation_strings":["Educational Testing Service"],"affiliations":[{"raw_affiliation_string":"Educational Testing Service","institution_ids":["https://openalex.org/I1341030882"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086079434"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.7522,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.96858627,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"579","last_page":"587"},"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":0.9991000294685364,"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/T10260","display_name":"Software Engineering Research","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8305476903915405},{"id":"https://openalex.org/keywords/compounding","display_name":"Compounding","score":0.8294638395309448},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7644052505493164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6320158243179321},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6029372811317444},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5773833990097046},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5519042015075684},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5375997424125671},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5309122800827026},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5134580731391907},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.487605482339859},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4652344584465027},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.32724449038505554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8305476903915405},{"id":"https://openalex.org/C207673951","wikidata":"https://www.wikidata.org/wiki/Q1303150","display_name":"Compounding","level":2,"score":0.8294638395309448},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7644052505493164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6320158243179321},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6029372811317444},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5773833990097046},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5519042015075684},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5375997424125671},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5309122800827026},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5134580731391907},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.487605482339859},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4652344584465027},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32724449038505554},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C159110408","wikidata":"https://www.wikidata.org/wiki/Q121176","display_name":"Nursing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/e14-1061","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-1061","pdf_url":"https://aclanthology.org/E14-1061.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.710.7848","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.710.7848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.uni-muenchen.de/%7Efraser/pubs/cap_eacl2014.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/e14-1061","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-1061","pdf_url":"https://aclanthology.org/E14-1061.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250332179.pdf","grobid_xml":"https://content.openalex.org/works/W2250332179.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1815552937","https://openalex.org/W1819520634","https://openalex.org/W1868901511","https://openalex.org/W2016856586","https://openalex.org/W2080012968","https://openalex.org/W2101105183","https://openalex.org/W2117642127","https://openalex.org/W2124807415","https://openalex.org/W2125768350","https://openalex.org/W2127589427","https://openalex.org/W2134800885","https://openalex.org/W2147880316","https://openalex.org/W2155539936","https://openalex.org/W2159755860","https://openalex.org/W2163353449","https://openalex.org/W2250526231","https://openalex.org/W2401109438","https://openalex.org/W2595715041"],"related_works":["https://openalex.org/W2466239135","https://openalex.org/W1946517836","https://openalex.org/W4387516256","https://openalex.org/W2470346308","https://openalex.org/W94067344","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165"],"abstract_inverted_index":{"Compounding":[0],"in":[1,95,109],"morphologically":[2],"rich":[3],"languages":[4],"is":[5],"a":[6,28],"highly":[7],"productive":[8],"process":[9],"which":[10,91],"often":[11],"causes":[12],"SMT":[13,79],"approaches":[14],"to":[15,41,58,69],"fail":[16],"because":[17],"of":[18,49,105],"unseen":[19],"words.":[20],"We":[21,73],"present":[22],"an":[23,42],"approach":[24,76],"for":[25,37,46],"translation":[26,88],"into":[27,34,52,77],"compounding":[29],"language":[30,68],"that":[31,82],"splits":[32],"compounds":[33,53,84],"simple":[35,50],"words":[36,51],"training":[38,97],"and,":[39],"due":[40],"underspecified":[43],"representation,":[44],"allows":[45],"free":[47],"merging":[48],"after":[54],"translation.":[55],"In":[56],"contrast":[57],"previous":[59],"approaches,":[60],"we":[61],"use":[62],"features":[63],"projected":[64],"from":[65],"the":[66,86,96,103],"source":[67],"predict":[70],"compound":[71,107],"mergings.":[72],"integrate":[74],"our":[75],"end-to-end":[78],"and":[80],"show":[81],"many":[83],"matching":[85],"reference":[87],"are":[89],"produced":[90],"did":[92],"not":[93],"appear":[94],"data.":[98],"Additional":[99],"manual":[100],"evaluations":[101],"support":[102],"usefulness":[104],"generalizing":[106],"formation":[108],"SMT.":[110]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}