{"id":"https://openalex.org/W2514698017","doi":"https://doi.org/10.18653/v1/p16-1103","title":"Synthesizing Compound Words for Machine Translation","display_name":"Synthesizing Compound Words for Machine Translation","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2514698017","doi":"https://doi.org/10.18653/v1/p16-1103","mag":"2514698017"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p16-1103","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1103","pdf_url":"https://www.aclweb.org/anthology/P16-1103.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 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P16-1103.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066163749","display_name":"Austin Matthews","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Austin Matthews","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University Pittsburgh, PA 15213, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047005963","display_name":"Eva Schlinger","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eva Schlinger","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University Pittsburgh, PA 15213, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103284923","display_name":"Alon Lavie","orcid":"https://orcid.org/0000-0001-9934-6519"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alon Lavie","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University Pittsburgh, PA 15213, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111222692","display_name":"Chris Dyer","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Dyer","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University Pittsburgh, PA 15213, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066163749"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.1424,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90641296,"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":"1085","last_page":"1094"},"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":0.9995999932289124,"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/T10759","display_name":"Translation Studies and Practices","score":0.9781000018119812,"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/computer-science","display_name":"Computer science","score":0.8339124321937561},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7783621549606323},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7666168212890625},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7274121046066284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6865728497505188},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.6642357707023621},{"id":"https://openalex.org/keywords/compound","display_name":"Compound","score":0.6390966176986694},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5739046335220337},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5311012864112854},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.521939218044281},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.46494120359420776},{"id":"https://openalex.org/keywords/transfer-based-machine-translation","display_name":"Transfer-based machine translation","score":0.4423541724681854},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.31297916173934937},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23414009809494019}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8339124321937561},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7783621549606323},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7666168212890625},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7274121046066284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6865728497505188},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.6642357707023621},{"id":"https://openalex.org/C2674912","wikidata":"https://www.wikidata.org/wiki/Q245423","display_name":"Compound","level":2,"score":0.6390966176986694},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5739046335220337},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5311012864112854},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.521939218044281},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.46494120359420776},{"id":"https://openalex.org/C130597682","wikidata":"https://www.wikidata.org/wiki/Q6961922","display_name":"Transfer-based machine translation","level":4,"score":0.4423541724681854},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.31297916173934937},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23414009809494019},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p16-1103","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1103","pdf_url":"https://www.aclweb.org/anthology/P16-1103.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 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p16-1103","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1103","pdf_url":"https://www.aclweb.org/anthology/P16-1103.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 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2514698017.pdf","grobid_xml":"https://content.openalex.org/works/W2514698017.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W64777181","https://openalex.org/W237846910","https://openalex.org/W400322755","https://openalex.org/W645927007","https://openalex.org/W1522301498","https://openalex.org/W1815552937","https://openalex.org/W2006969979","https://openalex.org/W2037788937","https://openalex.org/W2064675550","https://openalex.org/W2100631779","https://openalex.org/W2106068492","https://openalex.org/W2115259925","https://openalex.org/W2116599427","https://openalex.org/W2118804972","https://openalex.org/W2134955506","https://openalex.org/W2141440284","https://openalex.org/W2144600658","https://openalex.org/W2152249239","https://openalex.org/W2155539936","https://openalex.org/W2155607551","https://openalex.org/W2157435188","https://openalex.org/W2164766438","https://openalex.org/W2169423212","https://openalex.org/W2250229103","https://openalex.org/W2250332179","https://openalex.org/W2252154714","https://openalex.org/W2964121744","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1559710535","https://openalex.org/W2566847733","https://openalex.org/W2010336863","https://openalex.org/W2962780935","https://openalex.org/W3204448004","https://openalex.org/W193726211","https://openalex.org/W4378619223","https://openalex.org/W2027317339","https://openalex.org/W2532807140","https://openalex.org/W2384400852"],"abstract_inverted_index":{"Most":[0],"machine":[1],"translation":[2,82,120],"systems":[3],"construct":[4],"translations":[5,135],"from":[6],"a":[7,27,43,57,72,126],"closed":[8],"vocabulary":[9],"of":[10,48,74,130],"target":[11,63],"word":[12,60],"forms,":[13],"posing":[14],"problems":[15],"for":[16,66],"translating":[17],"into":[18,56,136],"languages":[19],"that":[20,32,45,52,90],"have":[21],"productive":[22],"compounding":[23],"processes.":[24],"We":[25,122],"present":[26],"simple":[28],"and":[29,109,118,133],"effective":[30],"approach":[31],"deals":[33],"with":[34],"this":[35],"problem":[36],"in":[37,61,115],"two":[38],"phases.":[39],"First,":[40],"we":[41,70,92],"build":[42],"classifier":[44],"identifies":[46],"spans":[47,97],"the":[49,62,81],"input":[50],"text":[51],"can":[53,93,98],"be":[54,99],"translated":[55],"single":[58],"compound":[59,103],"language.":[64],"Then,":[65],"each":[67],"identified":[68],"span,":[69],"generate":[71],"pool":[73],"possible":[75,114],"compounds":[76],"which":[77],"are":[78,113],"added":[79],"to":[80],"model":[83,105],"as":[84],"\"synthetic\"":[85],"phrase":[86],"translations.":[87],"Experiments":[88],"reveal":[89],"(i)":[91],"effectively":[94],"predict":[95],"what":[96],"compounded;":[100],"(ii)":[101],"our":[102],"generation":[104],"produces":[106],"good":[107],"compounds;":[108],"(iii)":[110],"modest":[111],"improvements":[112],"end-to-end":[116],"English-German":[117],"English-Finnish":[119],"tasks.":[121],"additionally":[123],"introduce":[124],"KomposEval,":[125],"new":[127],"multi-reference":[128],"dataset":[129],"English":[131],"phrases":[132],"their":[134],"German":[137],"compounds.":[138]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}