{"id":"https://openalex.org/W2760463480","doi":"https://doi.org/10.18653/v1/w17-4117","title":"What do we need to know about an unknown word when parsing German","display_name":"What do we need to know about an unknown word when parsing German","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2760463480","doi":"https://doi.org/10.18653/v1/w17-4117","mag":"2760463480"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-4117","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4117","pdf_url":"https://www.aclweb.org/anthology/W17-4117.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 First Workshop on Subword and Character Level Models in NLP","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-4117.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007369154","display_name":"Bich-Ngoc Do","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099471","display_name":"Leibniz Institute for the German Language","ror":"https://ror.org/00hvwkt50","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210099471"]},{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Bich-Ngoc Do","raw_affiliation_strings":["Leibniz ScienceCampus Universitt Heidelberg / Institut fr Deutsche Sprache Mannheim  Germany","Leibniz ScienceCampus Universit\u00e4t Heidelberg / Institut f\u00fcr Deutsche Sprache Mannheim \u2663 Germany"],"affiliations":[{"raw_affiliation_string":"Leibniz ScienceCampus Universitt Heidelberg / Institut fr Deutsche Sprache Mannheim  Germany","institution_ids":["https://openalex.org/I4210099471"]},{"raw_affiliation_string":"Leibniz ScienceCampus Universit\u00e4t Heidelberg / Institut f\u00fcr Deutsche Sprache Mannheim \u2663 Germany","institution_ids":["https://openalex.org/I223822909","https://openalex.org/I4210099471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064974921","display_name":"Ines Rehbein","orcid":"https://orcid.org/0000-0002-9615-6389"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I4210099471","display_name":"Leibniz Institute for the German Language","ror":"https://ror.org/00hvwkt50","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210099471"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ines Rehbein","raw_affiliation_strings":["Leibniz ScienceCampus Universitt Heidelberg / Institut fr Deutsche Sprache Mannheim  Germany","Leibniz ScienceCampus Universit\u00e4t Heidelberg / Institut f\u00fcr Deutsche Sprache Mannheim \u2663 Germany"],"affiliations":[{"raw_affiliation_string":"Leibniz ScienceCampus Universitt Heidelberg / Institut fr Deutsche Sprache Mannheim  Germany","institution_ids":["https://openalex.org/I4210099471"]},{"raw_affiliation_string":"Leibniz ScienceCampus Universit\u00e4t Heidelberg / Institut f\u00fcr Deutsche Sprache Mannheim \u2663 Germany","institution_ids":["https://openalex.org/I223822909","https://openalex.org/I4210099471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023977688","display_name":"Anette Frank","orcid":"https://orcid.org/0000-0003-4706-9817"},"institutions":[{"id":"https://openalex.org/I4210099471","display_name":"Leibniz Institute for the German Language","ror":"https://ror.org/00hvwkt50","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210099471"]},{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anette Frank","raw_affiliation_strings":["Leibniz ScienceCampus Universitt Heidelberg / Institut fr Deutsche Sprache Mannheim  Germany","Leibniz ScienceCampus Universit\u00e4t Heidelberg / Institut f\u00fcr Deutsche Sprache Mannheim \u2663 Germany"],"affiliations":[{"raw_affiliation_string":"Leibniz ScienceCampus Universitt Heidelberg / Institut fr Deutsche Sprache Mannheim  Germany","institution_ids":["https://openalex.org/I4210099471"]},{"raw_affiliation_string":"Leibniz ScienceCampus Universit\u00e4t Heidelberg / Institut f\u00fcr Deutsche Sprache Mannheim \u2663 Germany","institution_ids":["https://openalex.org/I223822909","https://openalex.org/I4210099471"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007369154"],"corresponding_institution_ids":["https://openalex.org/I223822909","https://openalex.org/I4210099471"],"apc_list":null,"apc_paid":null,"fwci":0.2078,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65086674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T13629","display_name":"Text Readability and Simplification","score":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.8454514741897583},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.7933984398841858},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7761921286582947},{"id":"https://openalex.org/keywords/dependency-grammar","display_name":"Dependency grammar","score":0.7617099285125732},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7518750429153442},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7165851593017578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7038367986679077},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6872910857200623},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6269313097000122},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5797873139381409},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5551422834396362},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.4936004877090454},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13319414854049683},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12399229407310486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8454514741897583},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.7933984398841858},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7761921286582947},{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.7617099285125732},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7518750429153442},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7165851593017578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7038367986679077},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6872910857200623},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6269313097000122},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5797873139381409},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5551422834396362},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.4936004877090454},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13319414854049683},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12399229407310486},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w17-4117","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4117","pdf_url":"https://www.aclweb.org/anthology/W17-4117.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 First Workshop on Subword and Character Level Models in NLP","raw_type":"proceedings-article"},{"id":"pmh:oai:ids-pub.bsz-bw.de:8024","is_oa":true,"landing_page_url":"https://ids-pub.bsz-bw.de/frontdoor/index/index/docId/8024","pdf_url":null,"source":{"id":"https://openalex.org/S4306401750","display_name":"Publication Server of the Institute for German Language (Institute for German Language)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210099471","host_organization_name":"Leibniz Institute for the German Language","host_organization_lineage":["https://openalex.org/I4210099471"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceobject"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-4117","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4117","pdf_url":"https://www.aclweb.org/anthology/W17-4117.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 First Workshop on Subword and Character Level Models in NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6604464234","display_name":null,"funder_award_id":"SAS-2015","funder_id":"https://openalex.org/F4320334763","funder_display_name":"Leibniz-Gemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320334763","display_name":"Leibniz-Gemeinschaft","ror":"https://ror.org/01n6r0e97"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2760463480.pdf","grobid_xml":"https://content.openalex.org/works/W2760463480.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W153523274","https://openalex.org/W1505680913","https://openalex.org/W1522301498","https://openalex.org/W1523296404","https://openalex.org/W1632114991","https://openalex.org/W1860935423","https://openalex.org/W1899794420","https://openalex.org/W1938755728","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2101609803","https://openalex.org/W2110256520","https://openalex.org/W2155870214","https://openalex.org/W2250612198","https://openalex.org/W2250741237","https://openalex.org/W2250861254","https://openalex.org/W2251012068","https://openalex.org/W2251088156","https://openalex.org/W2251481301","https://openalex.org/W2417763662","https://openalex.org/W2497378173","https://openalex.org/W2611767671","https://openalex.org/W2949563612","https://openalex.org/W2951559648","https://openalex.org/W2963099225","https://openalex.org/W2963208801","https://openalex.org/W2963216505","https://openalex.org/W2964005834","https://openalex.org/W2964090065","https://openalex.org/W2964121744","https://openalex.org/W2964198424"],"related_works":["https://openalex.org/W2251084681","https://openalex.org/W4241489294","https://openalex.org/W2098784136","https://openalex.org/W287510790","https://openalex.org/W63925617","https://openalex.org/W2151754849","https://openalex.org/W2252142543","https://openalex.org/W2968543375","https://openalex.org/W2953770453","https://openalex.org/W4288558800"],"abstract_inverted_index":{"We":[0,24],"propose":[1],"a":[2,16,38,63,133],"new":[3,130],"type":[4],"of":[5,53,66,103,116],"subword":[6],"embedding":[7],"designed":[8],"to":[9,37,46,83],"provide":[10],"more":[11],"information":[12,76,99,118],"about":[13,100],"unknown":[14,105,120],"compounds,":[15],"major":[17],"source":[18],"for":[19,110,119],"OOV":[20],"words":[21,106],"in":[22,132],"German.":[23],"present":[25],"an":[26],"extrinsic":[27],"evaluation":[28,56],"where":[29],"we":[30,126],"use":[31],"the":[32,44,47,84,87,97,101,104,114,129],"compound":[33,60],"embeddings":[34,61,72,82,131],"as":[35],"input":[36],"neural":[39],"dependency":[40],"parser":[41],"and":[42,141],"compare":[43],"results":[45],"ones":[48],"obtained":[49],"with":[50],"other":[51],"types":[52],"embeddings.":[54],"Our":[55],"shows":[57],"that":[58,93,107,137],"adding":[59,80],"yields":[62],"significant":[64],"improvement":[65],"2%":[67],"LAS":[68],"over":[69],"using":[70],"word":[71],"when":[73],"no":[74],"POS":[75,81],"is":[77,95],"available.":[78],"When":[79],"input,":[85],"however,":[86],"effect":[88],"levels":[89],"out.":[90],"This":[91],"suggests":[92],"it":[94],"not":[96],"missing":[98],"semantics":[102],"causes":[108],"problems":[109],"parsing":[111],"German,":[112],"but":[113],"lack":[115],"morphological":[117],"words.":[121],"To":[122],"augment":[123],"our":[124],"evaluation,":[125],"also":[127],"test":[128],"language":[134],"modelling":[135],"task":[136],"requires":[138],"both":[139],"syntactic":[140],"semantic":[142],"information.":[143]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}