11.30 – 12.00 Semantic job search- showcaseJakub Zavrel, CEO Textkernel
ESCO and Semantic Search & Match
for Jobs and People
Brussels, 9/10 October 2017
What is
Semantic
Search?Find what you mean, not what you type
Search for things, not for strings
Semantic Search & Match. Why?More relevant candidates, faster!
1. More candidates: Expanding words to conceptsNo guessing what candidate wrote in the resume
2. Relevant candidates: Better filtering and rankingAvoid wrong matches by understanding context
3. Work faster- Start working on the most promising candidates first
- Be a great searcher without advanced Boolean search
- Use documents (jobs, resumes) to start automated searches
2 word user query = 35+ system query
Three Elements of Semantic
Search
Document
understanding
Domain
knowledge
Machine
Learning
➔ CV & job parsing
➔ Information extraction
➔ Taxonomies
➔ Ontologies
➔ Skills
➔ Keywords
➔ Algorithms learn from
a large set of data
➔ Learning to Rank
➔ Deep Learning
Match!
Search!
CV Extraction
job=Java Developercity=Amsterdamlangskill=Germanexperience=7
CV MatchNormalizer
job=23branch=ITlangskill=DEexperience=7loc=Amsterdam
Vacancy MatchNormalizer
job=23branch=IT
langskill=DEexperience=5..10
loc=Amsterdam+10
Vacancy Extraction
job=Java Ontwikkelarcity=Amsterdamlangskill=Duitsexperience=7
Match!
Match! models construct the Search! Data Model out of extracted information.
The XML fits the Search! Data Model and is semantically enriched when INDEXING.
The result is a QUERY that fits the Search! Data Model. It is semantically enriched when executed
Data Model
job branch langskill location
experience
ESCO – What it means for us
• Direct availability of semantic query enrichments in 26 EU languages (on top of 6 that we developed internally)
• Cross lingual search because of aligned taxonomies.
• Occupation to skills expansion for better search
Demo
Some numbers on coverageNumbers of results?
Occupation ESCO Essential ESCO Optional TK Skills
ICT Security Technician 0 2230 2255
ICT Network Technician 0 128 454
Data Scientist 21 92 200
Office Manager 23 187 9514
Sales Manager 17 47 164
Sales Assistant 1 1 543
Waiter/waitress 0 0 207
Receptionist 190 193 197
Some numbers on coverageHow is the general coverage of the data by ESCO?
Some numbers on coverageHow is the general coverage of the data by ESCO?
SummaryTextkernel will support ESCO v1 in its Search & Match products.
Direct availability of semantic enrichments in 26 EU languages.
A standard to evolve.
Further steps needed to address:• Gap between ESCO terms and actual language use
• Maintenance process