{"id":"https://openalex.org/W2511594824","doi":"https://doi.org/10.18653/v1/w16-1807","title":"Top a Splitter: Using Distributional Semantics for Improving Compound Splitting","display_name":"Top a Splitter: Using Distributional Semantics for Improving Compound Splitting","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2511594824","doi":"https://doi.org/10.18653/v1/w16-1807","mag":"2511594824"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-1807","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-1807","pdf_url":"https://www.aclweb.org/anthology/W16-1807.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 12th Workshop on Multiword Expressions","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-1807.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056458616","display_name":"Patrick Ziering","orcid":null},"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":true,"raw_author_name":"Patrick Ziering","raw_affiliation_strings":["Institute for Natural Language Processing University of Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101789010","display_name":"Stefan M\u00fcller","orcid":"https://orcid.org/0000-0003-4413-5313"},"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":"Stefan M\u00fcller","raw_affiliation_strings":["Institute for Natural Language Processing University of Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022407073","display_name":"Lonneke van der Plas","orcid":"https://orcid.org/0000-0002-2871-2574"},"institutions":[{"id":"https://openalex.org/I197854408","display_name":"University of Malta","ror":"https://ror.org/03a62bv60","country_code":"MT","type":"education","lineage":["https://openalex.org/I197854408"]}],"countries":["MT"],"is_corresponding":false,"raw_author_name":"Lonneke van der Plas","raw_affiliation_strings":["Institute of Linguistics University of Malta, Malta"],"affiliations":[{"raw_affiliation_string":"Institute of Linguistics University of Malta, Malta","institution_ids":["https://openalex.org/I197854408"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056458616"],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":2.6504,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.92085238,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"55"},"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":0.9994000196456909,"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/T12031","display_name":"Speech and dialogue systems","score":0.9919999837875366,"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/splitter","display_name":"Splitter","score":0.7842844724655151},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.7111608386039734},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6646704077720642},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6270615458488464},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5608178973197937},{"id":"https://openalex.org/keywords/compound","display_name":"Compound","score":0.5084039568901062},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45596641302108765},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4408072829246521},{"id":"https://openalex.org/keywords/distributional-semantics","display_name":"Distributional semantics","score":0.4234044849872589},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.3552895784378052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33872026205062866},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21596309542655945},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21213477849960327},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16372936964035034},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.09459131956100464}],"concepts":[{"id":"https://openalex.org/C2777403171","wikidata":"https://www.wikidata.org/wiki/Q7578732","display_name":"Splitter","level":2,"score":0.7842844724655151},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7111608386039734},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6646704077720642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6270615458488464},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5608178973197937},{"id":"https://openalex.org/C2674912","wikidata":"https://www.wikidata.org/wiki/Q245423","display_name":"Compound","level":2,"score":0.5084039568901062},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45596641302108765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4408072829246521},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.4234044849872589},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.3552895784378052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33872026205062866},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21596309542655945},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21213477849960327},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16372936964035034},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.09459131956100464},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w16-1807","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-1807","pdf_url":"https://www.aclweb.org/anthology/W16-1807.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 12th Workshop on Multiword Expressions","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-1807","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-1807","pdf_url":"https://www.aclweb.org/anthology/W16-1807.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 12th Workshop on Multiword Expressions","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G762232396","display_name":null,"funder_award_id":"Project","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/W2511594824.pdf","grobid_xml":"https://content.openalex.org/works/W2511594824.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W25517462","https://openalex.org/W1480857181","https://openalex.org/W1522263329","https://openalex.org/W1815552937","https://openalex.org/W1984052055","https://openalex.org/W2016856586","https://openalex.org/W2057399676","https://openalex.org/W2117082935","https://openalex.org/W2134955506","https://openalex.org/W2135413937","https://openalex.org/W2163353449","https://openalex.org/W2251400472","https://openalex.org/W2251481301","https://openalex.org/W2254518460","https://openalex.org/W2293483433","https://openalex.org/W2401109438","https://openalex.org/W2463932830","https://openalex.org/W2468765526","https://openalex.org/W2977947870"],"related_works":["https://openalex.org/W2376862957","https://openalex.org/W2963364736","https://openalex.org/W2508696262","https://openalex.org/W2808113865","https://openalex.org/W3162545634","https://openalex.org/W3046869600","https://openalex.org/W2112408611","https://openalex.org/W3086187336","https://openalex.org/W2250286003","https://openalex.org/W4366284213"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,26],"flexible":[3],"method":[4],"that":[5,35],"rearranges":[6],"the":[7,20,39],"ranked":[8],"output":[9],"of":[10,15,41],"compound":[11,43],"splitters":[12],"(i.e.,":[13],"decomposers":[14],"one-word":[16],"compounds":[17],"such":[18],"as":[19],"German":[21],"Kinderlied":[22],"'children's":[23],"song')":[24],"using":[25],"distributional":[27],"semantics":[28],"model.":[29],"In":[30],"an":[31],"experiment,":[32],"we":[33],"show":[34],"our":[36],"re-ranker":[37],"improves":[38],"quality":[40],"various":[42],"splitters.":[44]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-16T15:07:20.185449","created_date":"2025-10-10T00:00:00"}
