{"id":"https://openalex.org/W2781746009","doi":"https://doi.org/10.1007/978-3-319-73706-5_6","title":"Word and Sentence Segmentation in German: Overcoming Idiosyncrasies in the Use of Punctuation in Private Communication","display_name":"Word and Sentence Segmentation in German: Overcoming Idiosyncrasies in the Use of Punctuation in Private Communication","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2781746009","doi":"https://doi.org/10.1007/978-3-319-73706-5_6","mag":"2781746009"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-73706-5_6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-73706-5_6","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-319-73706-5_6.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","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-319-73706-5_6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073033943","display_name":"Kyoko Sugisaki","orcid":"https://orcid.org/0000-0002-2851-6207"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Kyoko Sugisaki","raw_affiliation_strings":["German department, University of Zurich, Sch\u00f6nberggasse 9, 8001, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"German department, University of Zurich, Sch\u00f6nberggasse 9, 8001, Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5073033943"],"corresponding_institution_ids":["https://openalex.org/I202697423"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.2715,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.50967096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"62","last_page":"71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.998199999332428,"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/punctuation","display_name":"Punctuation","score":0.9199247360229492},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.79233717918396},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.7911978363990784},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7341662049293518},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7085646390914917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6311323642730713},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6219849586486816},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.5686237812042236},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5375900268554688},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5368540287017822},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5201016664505005},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.4885329008102417},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39082929491996765},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.29684948921203613}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.9199247360229492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79233717918396},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.7911978363990784},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7341662049293518},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7085646390914917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6311323642730713},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6219849586486816},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.5686237812042236},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5375900268554688},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5368540287017822},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5201016664505005},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.4885329008102417},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39082929491996765},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.29684948921203613},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-319-73706-5_6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-73706-5_6","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-319-73706-5_6.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"},{"id":"pmh:oai:www.zora.uzh.ch:149515","is_oa":true,"landing_page_url":null,"pdf_url":"https://www.zora.uzh.ch/id/eprint/149515/1/sugisaki2017b.pdf","source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sugisaki, Kyoko  (2017). Word and sentence segmentation in german: Overcoming idiosyncrasies in the use of punctuation in private communication.  In: 27th International Conference, GSCL 2017, Berlin, September 2017, s.n..","raw_type":"Conference or Workshop Item"},{"id":"doi:10.5167/uzh-149515","is_oa":true,"landing_page_url":"https://doi.org/10.5167/uzh-149515","pdf_url":null,"source":{"id":"https://openalex.org/S7407051291","display_name":"Universit\u00e4t Z\u00fcrich, ZORA","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.1007/978-3-319-73706-5_6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-73706-5_6","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-319-73706-5_6.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":[],"awards":[{"id":"https://openalex.org/G5939478842","display_name":"The evolution of genres between standardization and variation: The case of picture post cards. Text and corpus driven studies of patterns of private everyday and tele communication.","funder_award_id":"160238","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2781746009.pdf","grobid_xml":"https://content.openalex.org/works/W2781746009.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W130850236","https://openalex.org/W199541590","https://openalex.org/W1522263329","https://openalex.org/W1614298861","https://openalex.org/W2119518919","https://openalex.org/W2121227244","https://openalex.org/W2121764873","https://openalex.org/W2128634885","https://openalex.org/W2129999749","https://openalex.org/W2147880316","https://openalex.org/W2183656857","https://openalex.org/W2403707901","https://openalex.org/W2404954229","https://openalex.org/W2407523058","https://openalex.org/W2493916176","https://openalex.org/W2509343702","https://openalex.org/W2511239188","https://openalex.org/W4206192903"],"related_works":["https://openalex.org/W2365612482","https://openalex.org/W2995505879","https://openalex.org/W2408387521","https://openalex.org/W2082176356","https://openalex.org/W3107535086","https://openalex.org/W4378945288","https://openalex.org/W2124727305","https://openalex.org/W1490831147","https://openalex.org/W4385570509","https://openalex.org/W2125145484"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,17,22,58,64],"segmentation":[6],"system":[7],"for":[8],"German":[9],"texts.":[10],"We":[11,30],"apply":[12],"conditional":[13],"random":[14],"fields":[15],"(CRF),":[16],"statistical":[18],"sequential":[19],"model,":[20],"to":[21],"type":[23],"of":[24,61,66],"text":[25],"used":[26,68],"in":[27,63,69],"private":[28,70],"communication.":[29,71],"show":[31],"that":[32,45],"by":[33,38],"segmenting":[34],"individual":[35],"punctuation,":[36],"and":[37,44,55],"taking":[39],"into":[40],"account":[41],"freestanding":[42],"lines":[43],"using":[46],"unsupervised":[47],"word":[48],"representation":[49],"(i.":[50],"e.,":[51],"Brown":[52],"clustering,":[53],"Word2Vec":[54],"Fasttext)":[56],"achieved":[57],"label":[59],"accuracy":[60],"96%":[62],"corpus":[65],"postcards":[67]},"counts_by_year":[{"year":2023,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}