{"id":"https://openalex.org/W2250361849","doi":"https://doi.org/10.3115/v1/w15-1517","title":"Word Embeddings vs Word Types for Sequence Labeling: the Curious Case of CV Parsing","display_name":"Word Embeddings vs Word Types for Sequence Labeling: the Curious Case of CV Parsing","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2250361849","doi":"https://doi.org/10.3115/v1/w15-1517","mag":"2250361849"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w15-1517","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w15-1517","pdf_url":"https://aclanthology.org/W15-1517.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 1st Workshop on Vector Space Modeling for Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W15-1517.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028832482","display_name":"Melanie Tosik","orcid":null},"institutions":[{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Melanie Tosik","raw_affiliation_strings":["Textkernel B.V . University of Potsdam Amsterdam , Netherlands","University of Potsdam #N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Textkernel B.V . University of Potsdam Amsterdam , Netherlands","institution_ids":["https://openalex.org/I176453806"]},{"raw_affiliation_string":"University of Potsdam #N#","institution_ids":["https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018685899","display_name":"Carsten Lygteskov Hansen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carsten Lygteskov Hansen","raw_affiliation_strings":["Department of Linguistics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010809562","display_name":"Gerard Goossen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerard Goossen","raw_affiliation_strings":["Department of Linguistics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090585637","display_name":"Mihai Rotaru","orcid":"https://orcid.org/0000-0002-4847-1923"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mihai Rotaru","raw_affiliation_strings":["Department of Linguistics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4083,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.59460251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"128"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9821000099182129,"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":0.8070977330207825},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.8039451837539673},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7960152626037598},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.7701537609100342},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.7507146596908569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7292688488960266},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6788053512573242},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5488704442977905},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4991018772125244},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.47446995973587036},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4599730968475342},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4268670082092285},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1371953785419464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8070977330207825},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.8039451837539673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7960152626037598},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.7701537609100342},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.7507146596908569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7292688488960266},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6788053512573242},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5488704442977905},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4991018772125244},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.47446995973587036},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4599730968475342},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4268670082092285},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1371953785419464},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/v1/w15-1517","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w15-1517","pdf_url":"https://aclanthology.org/W15-1517.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 1st Workshop on Vector Space Modeling for Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/v1/w15-1517","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w15-1517","pdf_url":"https://aclanthology.org/W15-1517.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 1st Workshop on Vector Space Modeling for Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250361849.pdf","grobid_xml":"https://content.openalex.org/works/W2250361849.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1623072288","https://openalex.org/W2051669046","https://openalex.org/W2051791742","https://openalex.org/W2099196804","https://openalex.org/W2107611725","https://openalex.org/W2117130368","https://openalex.org/W2141599568","https://openalex.org/W2147880316","https://openalex.org/W2155169782","https://openalex.org/W2158139315","https://openalex.org/W2979401726"],"related_works":["https://openalex.org/W2962906565","https://openalex.org/W2798423868","https://openalex.org/W3027026357","https://openalex.org/W3015678144","https://openalex.org/W3126392069","https://openalex.org/W2109665237","https://openalex.org/W2996257819","https://openalex.org/W2076440176","https://openalex.org/W3136048405","https://openalex.org/W2045514505"],"abstract_inverted_index":{"We":[0],"explore":[1],"new":[2],"methods":[3],"of":[4,20,59,82,91,96],"improving":[5],"Curriculum":[6],"Vit\u00e6":[7],"(CV)":[8],"parsing":[9],"for":[10,36],"German":[11,60],"documents":[12],"by":[13,70],"applying":[14],"recent":[15],"research":[16],"on":[17,44,64,102],"the":[18,30,45,65,71,75,92,97],"application":[19],"word":[21,31,51,76,98],"embeddings":[22,32,52,77,99],"in":[23],"Natural":[24],"Language":[25],"Processing":[26],"(NLP).Our":[27],"approach":[28],"integrates":[29,74],"as":[33],"input":[34],"features":[35],"a":[37,56,80],"probabilistic":[38],"sequence":[39],"labeling":[40],"model":[41,72],"that":[42],"relies":[43],"Conditional":[46],"Random":[47],"Field":[48],"(CRF)":[49],"framework.Best-performing":[50],"are":[53,68,86],"generated":[54],"from":[55],"large":[57],"sample":[58],"CVs.The":[61],"best":[62],"results":[63],"extraction":[66],"task":[67],"obtained":[69],"which":[73],"together":[78],"with":[79],"number":[81],"hand-crafted":[83],"features.The":[84],"improvements":[85],"consistent":[87],"throughout":[88],"different":[89],"sections":[90],"target":[93],"documents.The":[94],"effect":[95],"is":[100],"strongest":[101],"semi-structured,":[103],"out-of-sample":[104],"data.":[105]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-08-19T15:00:24.278416","created_date":"2025-10-10T00:00:00"}