{"id":"https://openalex.org/W2782159432","doi":"https://doi.org/10.1007/978-3-319-73706-5_3","title":"The Devil is in the Details: Parsing Unknown German Words","display_name":"The Devil is in the Details: Parsing Unknown German Words","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2782159432","doi":"https://doi.org/10.1007/978-3-319-73706-5_3","mag":"2782159432"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-73706-5_3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-73706-5_3","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-319-73706-5_3.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-319-73706-5_3.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051512108","display_name":"Daniel Dakota","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel Dakota","raw_affiliation_strings":["Department of Linguistics, Indiana University, Bloomington, USA"],"affiliations":[{"raw_affiliation_string":"Department of Linguistics, Indiana University, Bloomington, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051512108"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01388725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"39"},"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":0.9998999834060669,"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":0.9907000064849854,"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/treebank","display_name":"Treebank","score":0.9020789265632629},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8990126848220825},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.8143943548202515},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6797494888305664},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6773971319198608},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6769598722457886},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.6736658811569214},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5191954374313354},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4650750160217285},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1414499580860138},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10641181468963623}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.9020789265632629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8990126848220825},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8143943548202515},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6797494888305664},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6773971319198608},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6769598722457886},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.6736658811569214},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5191954374313354},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4650750160217285},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1414499580860138},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10641181468963623},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-319-73706-5_3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-73706-5_3","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-319-73706-5_3.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-319-73706-5_3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-73706-5_3","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-319-73706-5_3.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2782159432.pdf","grobid_xml":"https://content.openalex.org/works/W2782159432.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W3313028","https://openalex.org/W108437174","https://openalex.org/W1518867723","https://openalex.org/W1973346430","https://openalex.org/W1974551340","https://openalex.org/W2002685786","https://openalex.org/W2052847729","https://openalex.org/W2109000768","https://openalex.org/W2113691817","https://openalex.org/W2121227244","https://openalex.org/W2128634885","https://openalex.org/W2132726600","https://openalex.org/W2132890663","https://openalex.org/W2135843243","https://openalex.org/W2139621418","https://openalex.org/W2143391265","https://openalex.org/W2148651755","https://openalex.org/W2152561660","https://openalex.org/W2166159129","https://openalex.org/W2172242228","https://openalex.org/W2183656857","https://openalex.org/W2236649376","https://openalex.org/W2250562110","https://openalex.org/W2251088156","https://openalex.org/W2251356573","https://openalex.org/W2251987034","https://openalex.org/W2283658385","https://openalex.org/W2413158316","https://openalex.org/W2569308312","https://openalex.org/W2646728047"],"related_works":["https://openalex.org/W1043255351","https://openalex.org/W2135057643","https://openalex.org/W2109902858","https://openalex.org/W1533278948","https://openalex.org/W1781980207","https://openalex.org/W2951759144","https://openalex.org/W28706907","https://openalex.org/W2949524199","https://openalex.org/W2017946383","https://openalex.org/W2104399512"],"abstract_inverted_index":{"The":[0],"statistical":[1],"parsing":[2],"of":[3,12,19,23,40,69],"morphologically":[4],"rich":[5],"languages":[6,110],"is":[7],"hindered":[8],"by":[9],"the":[10,20,61,96],"inability":[11],"parsers":[13,87],"to":[14,59,71,115],"collect":[15],"solid":[16],"statistics":[17],"because":[18],"large":[21],"number":[22],"word":[24,82,138],"types":[25],"in":[26,78],"such":[27],"languages.":[28],"There":[29],"are":[30],"however":[31],"two":[32,85],"separate":[33],"but":[34],"connected":[35],"problems,":[36],"reducing":[37],"data":[38,73],"sparsity":[39,74],"known":[41],"words":[42,93],"and":[43,46,91,117,136],"handling":[44],"rare":[45,90,135],"unknown":[47,81,92,137],"words.":[48],"Methods":[49],"for":[50,108,134],"tackling":[51],"one":[52],"problem":[53],"may":[54],"inadvertently":[55],"negatively":[56],"impact":[57],"methods":[58,103],"handle":[60,89],"other.":[62],"We":[63,100],"perform":[64],"a":[65,125,130],"tightly":[66],"controlled":[67],"set":[68],"experiments":[70],"reduce":[72],"through":[75],"class-based":[76],"representations":[77],"combination":[79],"with":[80,84],"signatures":[83],"PCFG-LA":[86],"that":[88,102,104,118],"differently":[94],"on":[95],"German":[97],"TiGer":[98],"treebank.":[99],"demonstrate":[101],"have":[105],"improved":[106],"results":[107,123],"other":[109],"do":[111],"not":[112],"transfer":[113],"directly":[114],"German,":[116],"we":[119],"can":[120],"obtain":[121],"better":[122],"using":[124],"simplistic":[126],"model":[127,133],"rather":[128],"than":[129],"more":[131],"generalized":[132],"handling.":[139]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}