{"id":"https://openalex.org/W4416035749","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1375","title":"Improving Online Job Advertisement Analysis via Compositional Entity Extraction","display_name":"Improving Online Job Advertisement Analysis via Compositional Entity Extraction","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035749","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1375"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1375","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1375","pdf_url":"https://aclanthology.org/2025.emnlp-main.1375.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1375.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000399604","display_name":"Kai Kr\u00fcger","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kai Kr\u00fcger","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081958720","display_name":"Johanna Binnewitt","orcid":"https://orcid.org/0000-0001-9513-9045"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Johanna Binnewitt","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308902","display_name":"Kathrin Ehmann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kathrin Ehmann","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005917876","display_name":"Stefan Winnige","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Winnige","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032877157","display_name":"Alan Akbik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alan Akbik","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5000399604"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40115339,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27035","last_page":"27053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.5821999907493591,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.5821999907493591,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.10350000113248825,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.07289999723434448,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/extraction","display_name":"Extraction (chemistry)","score":0.2992999851703644},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.2797999978065491},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.27730000019073486},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27480000257492065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5824000239372253},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.4544000029563904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3499000072479248},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2493000030517578},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.24740000069141388}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1375","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1375","pdf_url":"https://aclanthology.org/2025.emnlp-main.1375.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1375","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1375","pdf_url":"https://aclanthology.org/2025.emnlp-main.1375.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035749.pdf","grobid_xml":"https://content.openalex.org/works/W4416035749.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,51,106],"compositional":[3,118],"entity":[4,40],"modeling":[5,33],"framework":[6],"for":[7],"requirement":[8],"extraction":[9],"from":[10,28],"Online":[11],"Job":[12],"Advertisements":[13],"(OJAs).To":[14],"more":[15],"accurately":[16],"capture":[17],"the":[18,26,60,77,90,98],"structure":[19],"of":[20,54,63,92,101,123],"requirements":[21],"in":[22],"OJAs,":[23],"we":[24,48,104],"reframe":[25],"task":[27],"identifying":[29],"single-span":[30],"annotations":[31],"to":[32,88],"complex,":[34],"tree-like":[35],"structures":[36],"that":[37],"connect":[38],"atomic":[39],"types":[41,122],"via":[42],"typed":[43],"relationships.Based":[44],"on":[45,94,110],"this":[46,95],"schema,":[47],"introduce":[49],"GOJA,":[50],"high-quality":[52],"dataset":[53],"500":[55],"German":[56],"job":[57,64,112],"ads.GOJA":[58],"captures":[59],"internal":[61],"semantics":[62],"requirements,":[65],"including":[66],"roles,":[67],"tools,":[68],"experience":[69],"levels,":[70],"attitudes,":[71],"and":[72,84],"their":[73],"functional":[74],"context.We":[75],"describe":[76],"annotation":[78],"process,":[79],"report":[80],"strong":[81],"inter-annotator":[82],"agreement,":[83],"benchmark":[85],"transformer":[86],"models":[87],"demonstrate":[89],"feasibility":[91],"training":[93],"structure.To":[96],"illustrate":[97],"analytical":[99],"potential":[100],"our":[102,116],"approach,":[103],"present":[105],"focused":[107],"case":[108],"study":[109],"AI-related":[111],"requirements.We":[113],"show":[114],"how":[115],"proposed":[117],"representation":[119],"enables":[120],"new":[121],"labor":[124],"market":[125],"analyses.":[126]},"counts_by_year":[],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2025-11-08T00:00:00"}