Improved
More accurate names, certifications and job sections in parsing
about 1 month ago by ReadMe API
Résumé parsing, text parsing and Document OCR return more accurate names, certification names, contact details and job sections, for the ways of writing a résumé or a job posting listed below.
Action required
- Now: none.
POST /profile/parsing/file,POST /text/parsingandPOST /text/ocrkeep their parameters and their responses. - Later: none. Nothing in this update is deprecated.
What changed
- Letter-spaced names (Quicksilver): a candidate's name set in letter-spaced capitals is read as words, so the
first_name,last_nameandfull_nameof itsinfoare right far more often for such résumés; section headings set that way also read as words in the profile'stext. - Certification names with a colon or a bracket: a name such as
PMP (Project Management Professional)orLean Six Sigma: Green Beltcomes back as one certification instead of two pieces, in parsed résumés (the profile'scertificationsand those of itsexperiencesandeducations) and inPOST /text/parsing. - Cleaner certification names (
POST /text/parsing): no list separator at their end, their closing bracket kept, and line breaks or runs of spaces inside a name turned into one space, such asFührerschein (Klasse B)orPermis B. - Entity edges (
POST /text/parsing): entities come back without a list separator (,or;) or a line break at their start or end, with both parsing models, and theirstartandendinentitiesleave it out; skill and certification names that end in a hyphenated or multi-digit number come back whole, such asnist sp 800-207. - Job title and location (
output_object=job): the job'slocation(both parsing models) and itsname(Quicksilver) are the place and the job title written first in the posting, so a posting that mentions its head office or the manager the role reports to further down keeps its own city and title. - Contact details (
output_object=profile): thefirst_name,last_name,email,phoneandlocationof the profile'sinfoare the ones written first in the text, usually the candidate's own, not those of a referee named further down. - Job sections with Atlas (
output_object=job): a posting whose list bullets sit alone on their lines, or that holds long runs of empty lines, comes back with itssummary,requirements,responsibilitiesand other sections filled, and faster. - Copied sections with Atlas (
output_object=job): the sections copied from the posting keep every character where a line breaks mid-sentence, andrequirementsmore often includes the years of experience and the seniority a posting gives only in a header line, such asSenior, 15+ years. - Driving licences:
driving_licenseis found more often in parsed résumés: a licence written with several classes run together, such asPermis ABC, is read as its first class. - Document OCR sections:
POST /text/ocrreturns the whole page in thesectionsof each of itspages: joined together, a page's sections give back its full text, and on a PDF page with a text block made only of spaces, the sections before and after it come back as two entries.
Example
curl -X POST https://api.hrflow.ai/v1/text/parsing \
-H "X-API-KEY: <your_api_key>" \
-H "X-USER-EMAIL: <your_email>" \
-H "Content-Type: application/json" \
-d '{
"texts": ["<a job posting>"],
"parsing_model": "quicksilver",
"output_object": "job"
}'The response keeps the format documented in the reference; the job's name and location are the title and the place written first in the posting.