Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386566431> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4386566431 abstract "Writing a good job description is an important step in the online recruitment process to hire the best candidates. Most recruiters forget to include some relevant skills in the job description. These missing skills affect the performance of recruitment tasks such as job suggestions, job search, candidate recommendations, etc. Existing approaches are limited to contextual modelling, do not exploit inter-relational structures like job-job and job-skill relationships, and are not scalable. In this paper, we exploit these structural relationships using a graph-based approach. We propose a novel skill prediction framework called JobXMLC, which uses graph neural networks with skill attention to predict missing skills using job descriptions. JobXMLC enables joint learning over a job-skill graph consisting of 22.8K entities (jobs and skills) and 650K relationships. We experiment with real-world recruitment datasets to evaluate our proposed approach. We train JobXMLC on 20,298 job descriptions and 2,548 skills within 30 minutes on a single GPU machine. JobXMLC outperforms the state-of-the-art approaches by 6% in precision and 3% in recall. JobXMLC is 18X faster for training task and up to 634X faster in skill prediction on benchmark datasets enabling JobXMLC to scale up on larger datasets." @default.
- W4386566431 created "2023-09-10" @default.
- W4386566431 creator A5027667267 @default.
- W4386566431 creator A5063029157 @default.
- W4386566431 creator A5063145886 @default.
- W4386566431 creator A5068620258 @default.
- W4386566431 creator A5068667521 @default.
- W4386566431 creator A5077509916 @default.
- W4386566431 date "2023-01-01" @default.
- W4386566431 modified "2023-10-14" @default.
- W4386566431 title "JobXMLC: EXtreme Multi-Label Classification of Job Skills with Graph Neural Networks" @default.
- W4386566431 doi "https://doi.org/10.18653/v1/2023.findings-eacl.163" @default.
- W4386566431 hasPublicationYear "2023" @default.
- W4386566431 type Work @default.
- W4386566431 citedByCount "0" @default.
- W4386566431 crossrefType "proceedings-article" @default.
- W4386566431 hasAuthorship W4386566431A5027667267 @default.
- W4386566431 hasAuthorship W4386566431A5063029157 @default.
- W4386566431 hasAuthorship W4386566431A5063145886 @default.
- W4386566431 hasAuthorship W4386566431A5068620258 @default.
- W4386566431 hasAuthorship W4386566431A5068667521 @default.
- W4386566431 hasAuthorship W4386566431A5077509916 @default.
- W4386566431 hasBestOaLocation W43865664311 @default.
- W4386566431 hasConcept C119857082 @default.
- W4386566431 hasConcept C132525143 @default.
- W4386566431 hasConcept C13280743 @default.
- W4386566431 hasConcept C154945302 @default.
- W4386566431 hasConcept C15744967 @default.
- W4386566431 hasConcept C162324750 @default.
- W4386566431 hasConcept C165696696 @default.
- W4386566431 hasConcept C174954385 @default.
- W4386566431 hasConcept C185798385 @default.
- W4386566431 hasConcept C187736073 @default.
- W4386566431 hasConcept C205649164 @default.
- W4386566431 hasConcept C2718322 @default.
- W4386566431 hasConcept C2780451532 @default.
- W4386566431 hasConcept C38652104 @default.
- W4386566431 hasConcept C41008148 @default.
- W4386566431 hasConcept C48044578 @default.
- W4386566431 hasConcept C77088390 @default.
- W4386566431 hasConcept C77805123 @default.
- W4386566431 hasConcept C80444323 @default.
- W4386566431 hasConceptScore W4386566431C119857082 @default.
- W4386566431 hasConceptScore W4386566431C132525143 @default.
- W4386566431 hasConceptScore W4386566431C13280743 @default.
- W4386566431 hasConceptScore W4386566431C154945302 @default.
- W4386566431 hasConceptScore W4386566431C15744967 @default.
- W4386566431 hasConceptScore W4386566431C162324750 @default.
- W4386566431 hasConceptScore W4386566431C165696696 @default.
- W4386566431 hasConceptScore W4386566431C174954385 @default.
- W4386566431 hasConceptScore W4386566431C185798385 @default.
- W4386566431 hasConceptScore W4386566431C187736073 @default.
- W4386566431 hasConceptScore W4386566431C205649164 @default.
- W4386566431 hasConceptScore W4386566431C2718322 @default.
- W4386566431 hasConceptScore W4386566431C2780451532 @default.
- W4386566431 hasConceptScore W4386566431C38652104 @default.
- W4386566431 hasConceptScore W4386566431C41008148 @default.
- W4386566431 hasConceptScore W4386566431C48044578 @default.
- W4386566431 hasConceptScore W4386566431C77088390 @default.
- W4386566431 hasConceptScore W4386566431C77805123 @default.
- W4386566431 hasConceptScore W4386566431C80444323 @default.
- W4386566431 hasLocation W43865664311 @default.
- W4386566431 hasOpenAccess W4386566431 @default.
- W4386566431 hasPrimaryLocation W43865664311 @default.
- W4386566431 hasRelatedWork W112744582 @default.
- W4386566431 hasRelatedWork W1485630101 @default.
- W4386566431 hasRelatedWork W1525643724 @default.
- W4386566431 hasRelatedWork W2302028273 @default.
- W4386566431 hasRelatedWork W2331043530 @default.
- W4386566431 hasRelatedWork W2364921833 @default.
- W4386566431 hasRelatedWork W2498017833 @default.
- W4386566431 hasRelatedWork W2983785000 @default.
- W4386566431 hasRelatedWork W2997512100 @default.
- W4386566431 hasRelatedWork W4320031300 @default.
- W4386566431 isParatext "false" @default.
- W4386566431 isRetracted "false" @default.
- W4386566431 workType "article" @default.