{"id":"https://openalex.org/W2508899723","doi":"https://doi.org/10.18653/v1/w16-2012","title":"Letter Sequence Labeling for Compound Splitting","display_name":"Letter Sequence Labeling for Compound Splitting","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2508899723","doi":"https://doi.org/10.18653/v1/w16-2012","mag":"2508899723"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-2012","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2012","pdf_url":"https://www.aclweb.org/anthology/W16-2012.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 14th SIGMORPHON Workshop on Computational Research\n          in Phonetics, Phonology, and Morphology","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-2012.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101523859","display_name":"Jianqiang Ma","orcid":"https://orcid.org/0009-0009-8814-0609"},"institutions":[{"id":"https://openalex.org/I4210121707","display_name":"Institute of Linguistics","ror":"https://ror.org/02mrea437","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197","https://openalex.org/I4210121707"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Jianqiang Ma","raw_affiliation_strings":["SFB 833 and Department of Linguistics University of Tbingen, Germany","SFB 833 and Department of Linguistics University of T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SFB 833 and Department of Linguistics University of Tbingen, Germany","institution_ids":["https://openalex.org/I4210121707"]},{"raw_affiliation_string":"SFB 833 and Department of Linguistics University of T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048917104","display_name":"Verena Henrich","orcid":null},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]},{"id":"https://openalex.org/I4210121707","display_name":"Institute of Linguistics","ror":"https://ror.org/02mrea437","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197","https://openalex.org/I4210121707"]}],"countries":["CN","DE"],"is_corresponding":true,"raw_author_name":"Verena Henrich","raw_affiliation_strings":["SFB 833 and Department of Linguistics University of Tbingen, Germany","SFB 833 and Department of Linguistics University of T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SFB 833 and Department of Linguistics University of Tbingen, Germany","institution_ids":["https://openalex.org/I4210121707"]},{"raw_affiliation_string":"SFB 833 and Department of Linguistics University of T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108637841","display_name":"Erhard Hinrichs","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121707","display_name":"Institute of Linguistics","ror":"https://ror.org/02mrea437","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197","https://openalex.org/I4210121707"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Erhard Hinrichs","raw_affiliation_strings":["SFB 833 and Department of Linguistics University of Tbingen, Germany","SFB 833 and Department of Linguistics University of T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SFB 833 and Department of Linguistics University of Tbingen, Germany","institution_ids":["https://openalex.org/I4210121707"]},{"raw_affiliation_string":"SFB 833 and Department of Linguistics University of T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048917104"],"corresponding_institution_ids":["https://openalex.org/I4210121707","https://openalex.org/I8087733"],"apc_list":null,"apc_paid":null,"fwci":2.651,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.9205834,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"76","last_page":"81"},"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":0.9994999766349792,"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":0.995199978351593,"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/sequence-labeling","display_name":"Sequence labeling","score":0.7514903545379639},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7409034967422485},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7298624515533447},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6786901950836182},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6541811227798462},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6182446479797363},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5826225280761719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5312509536743164},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5040625333786011},{"id":"https://openalex.org/keywords/compound","display_name":"Compound","score":0.42178672552108765},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3833473026752472},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11515635251998901},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10735335946083069},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.0947025716304779},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09346026182174683},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06880497932434082}],"concepts":[{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.7514903545379639},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7409034967422485},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7298624515533447},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6786901950836182},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6541811227798462},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6182446479797363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5826225280761719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5312509536743164},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5040625333786011},{"id":"https://openalex.org/C2674912","wikidata":"https://www.wikidata.org/wiki/Q245423","display_name":"Compound","level":2,"score":0.42178672552108765},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3833473026752472},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11515635251998901},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10735335946083069},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0947025716304779},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09346026182174683},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06880497932434082},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w16-2012","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2012","pdf_url":"https://www.aclweb.org/anthology/W16-2012.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 14th SIGMORPHON Workshop on Computational Research\n          in Phonetics, Phonology, and Morphology","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-2012","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2012","pdf_url":"https://www.aclweb.org/anthology/W16-2012.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 14th SIGMORPHON Workshop on Computational Research\n          in Phonetics, Phonology, and Morphology","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5142944752","display_name":null,"funder_award_id":"project A3","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6036663555","display_name":null,"funder_award_id":"SFB 833","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2508899723.pdf","grobid_xml":"https://content.openalex.org/works/W2508899723.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W35711202","https://openalex.org/W179935507","https://openalex.org/W294504433","https://openalex.org/W314345615","https://openalex.org/W1480857181","https://openalex.org/W1531522183","https://openalex.org/W1796592579","https://openalex.org/W1815552937","https://openalex.org/W1819520634","https://openalex.org/W2016856586","https://openalex.org/W2036516910","https://openalex.org/W2070554026","https://openalex.org/W2129494713","https://openalex.org/W2134913565","https://openalex.org/W2143134347","https://openalex.org/W2147880316","https://openalex.org/W2160986985","https://openalex.org/W2163353449","https://openalex.org/W2164766438","https://openalex.org/W2250286003","https://openalex.org/W2250799792","https://openalex.org/W2250818747","https://openalex.org/W2251256599","https://openalex.org/W2251400472","https://openalex.org/W2251481301","https://openalex.org/W2407523058","https://openalex.org/W3089269909"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2376862957","https://openalex.org/W2508696262","https://openalex.org/W3162545634","https://openalex.org/W3086187336","https://openalex.org/W2385598138"],"abstract_inverted_index":{"For":[0],"languages":[1],"such":[2],"as":[3,12],"German":[4],"where":[5],"compounds":[6],"occur":[7],"frequently":[8],"and":[9,24],"are":[10,60],"written":[11],"single":[13],"tokens,":[14],"a":[15,42],"wide":[16],"variety":[17],"of":[18],"NLP":[19],"applications":[20],"benefits":[21],"from":[22],"recognizing":[23],"splitting":[25,35],"compounds.":[26],"As":[27],"the":[28,67],"traditional":[29],"word":[30,51],"frequency-based":[31],"approach":[32],"to":[33,54],"compound":[34,73],"has":[36],"several":[37],"drawbacks,":[38],"this":[39],"paper":[40],"introduces":[41],"letter":[43],"sequence":[44],"labeling":[45],"approach,":[46],"which":[47],"can":[48],"utilize":[49],"rich":[50],"form":[52],"features":[53],"build":[55],"discriminative":[56],"learning":[57],"models":[58],"that":[59,66],"optimized":[61],"for":[62],"splitting.":[63],"Experiments":[64],"show":[65],"proposed":[68],"method":[69],"significantly":[70],"outperforms":[71],"state-ofthe-art":[72],"splitters.":[74]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-05-30T09:04:40.226872","created_date":"2025-10-10T00:00:00"}