C11 Flashcards
1
Q
problems with rule-based approach for extracting information (eg. name from a CV)
A
- gets complex to accommodate for exceptions
- coverage is limited
2
Q
typical machine learning pipeline for parsing CVs
A
- preprocessing/OCR
- detection of CV pages
- section segmentation
- item segmentation
- phrase segmentation
3
Q
how does Textkernel match CVs to vacancies?
A
transform CVs and vacancies into vectors, where relevant CVs are close to a job
calculate the distance between CV and job vectors to make a classification
4
Q
how does Textkernel match CVs to vacancies?
A
transform CVs and vacancies into vectors, where relevant CVs are close to a job
calculate the distance between CV and job vectors to make a classification
