{"id":"https://openalex.org/W1815552937","doi":null,"title":"How to Avoid Burning Ducks: Combining Linguistic Analysis and Corpus Statistics for German Compound Processing","display_name":"How to Avoid Burning Ducks: Combining Linguistic Analysis and Corpus Statistics for German Compound Processing","publication_year":2010,"publication_date":"2010-07-15","ids":{"openalex":"https://openalex.org/W1815552937","mag":"1815552937"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.357.5777","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.357.5777","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/W/W10/W10-1734.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/A5004312061","display_name":"Fabienne Fritzinger","orcid":null,"observed_orcids":[]},"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":"Fabienne Fritzinger","raw_affiliation_strings":["University of stuttgart"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of stuttgart","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101957153","display_name":"Alexander Fraser","orcid":"https://orcid.org/0000-0003-4891-682X","observed_orcids":["https://orcid.org/0000-0003-4891-682X"]},"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":"Alexander Fraser","raw_affiliation_strings":["University of stuttgart"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of stuttgart","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":2.1141,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.8701573,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"224","last_page":"234"},"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/T12353","display_name":"Lexicography and Language Studies","score":0.0,"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"}},{"id":"https://openalex.org/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.0,"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":0.7799999713897705},{"id":"https://openalex.org/keywords/german-compounds","display_name":"German compounds","score":0.7919999957084656},{"id":"https://openalex.org/keywords/linguistic-analysis","display_name":"linguistic analysis","score":0.734000027179718},{"id":"https://openalex.org/keywords/corpus-statistics","display_name":"corpus statistics","score":0.7649999856948853},{"id":"https://openalex.org/keywords/phrase-based-machine-translation","display_name":"phrase-based statistical machine translation","score":0.8349999785423279},{"id":"https://openalex.org/keywords/german-english-translation","display_name":"German-English translation","score":0.8659999966621399},{"id":"https://openalex.org/keywords/data-sparsity","display_name":"data sparsity","score":0.8999999761581421}],"concepts":[{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.8519057631492615},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7371903657913208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7304127216339111},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7099274396896362},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6776140332221985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5929591655731201},{"id":"https://openalex.org/C2674912","wikidata":"https://www.wikidata.org/wiki/Q245423","display_name":"Compound","level":2,"score":0.550472617149353},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.49984240531921387},{"id":"https://openalex.org/C2776728590","wikidata":"https://www.wikidata.org/wiki/Q363948","display_name":"Contradiction","level":2,"score":0.49950480461120605},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.46623799204826355},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.44027701020240784},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1021832525730133},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.357.5777","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.357.5777","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/W/W10/W10-1734.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.434.1932","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.434.1932","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/~fraser/pubs/fritzinger_wmt2010.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.604.2731","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.604.2731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.statmt.org/wmt10/pdf/WMT35.pdf","raw_type":"text"},{"id":"mag:1815552937","doi":null,"is_oa":false,"landing_page_url":"https://www.cis.uni-muenchen.de/~fraser/pubs/fritzinger_wmt2010.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306421295","display_name":"Workshop on Statistical Machine Translation","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Workshop on Statistical Machine Translation","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W294504433","https://openalex.org/W1480857181","https://openalex.org/W1819520634","https://openalex.org/W2015350341","https://openalex.org/W2016856586","https://openalex.org/W2091944322","https://openalex.org/W2101105183","https://openalex.org/W2124807415","https://openalex.org/W2133512280","https://openalex.org/W2143134347","https://openalex.org/W2146574666","https://openalex.org/W2164766438","https://openalex.org/W2401109438"],"related_works":["https://openalex.org/W2250286003","https://openalex.org/W2016856586","https://openalex.org/W1480857181","https://openalex.org/W6910784142","https://openalex.org/W2163353449","https://openalex.org/W2135413937","https://openalex.org/W2626159181","https://openalex.org/W2080012968","https://openalex.org/W2940356711","https://openalex.org/W1819520634"],"abstract_inverted_index":{"Compound":[0],"splitting":[1,32,36],"is":[2],"an":[3],"important":[4],"prob-lem":[5],"in":[6,14,71],"many":[7],"NLP":[8],"applications":[9],"which":[10],"must":[11],"be":[12],"solved":[13],"order":[15],"to":[16,51,78],"address":[17,57],"issues":[18],"of":[19,73],"data":[20],"sparsity.":[21],"Previous":[22],"work":[23,42],"has":[24],"shown":[25],"that":[26],"lin-guistic":[27],"approaches":[28,41],"for":[29,44],"German":[30,50],"compound":[31],"produce":[33],"a":[34,53,79],"correct":[35],"more":[37],"often,":[38],"but":[39],"corpus-driven":[40,65],"best":[43],"phrase-based":[45],"statistical":[46,83],"machine":[47,84],"translation":[48,85],"from":[49],"English,":[52],"worrisome":[54],"contradiction.":[55],"We":[56],"this":[58],"situation":[59],"by":[60],"combining":[61],"linguistic":[62],"analysis":[63],"with":[64],"statistics":[66],"and":[67,82],"obtain-ing":[68],"better":[69],"results":[70],"terms":[72],"both":[74],"produc-ing":[75],"splittings":[76],"according":[77],"gold":[80],"standard":[81],"perfor-mance.":[86],"1":[87]},"counts_by_year":[{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}
