erecruiter expert system presenters: date. agenda review (wei 2 mins) – problem domain –...

17
eRecruiter Expert System Presenters: Date

Upload: winfred-hawkins

Post on 24-Dec-2015

214 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

eRecruiter Expert System

Presenters:Date

Page 2: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

Agenda

• Review (Wei 2 mins)– Problem domain– Overview of the system

• Milestones (Jon S. 2 mins)– Timeboxes– Deliverables

• Meetings with experts (Max or/and Jon M. 2 mins)– With Steve Saunder

• Nuts and Bolts (all 8 mins)– Work division– Implementation of each part of the system

• Demo and discussion (Jon S. 6 mins)

Page 3: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

Introduction and Overview

Page 4: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

eRecruiter• Problem domain:

– eRecruiter is an expert system that help judge a resume according to the knowledge extracted from a human expert.

• As an expert system:– Facts from resumes.– Templates to define the structure of facts and knowledge.– Inference rules for scoring and weighting facts and making decisions.– Explanation for explaining the results of judgments.

• Use cases of the system:– Quickly create a pool of qualified resumes.– Rank resumes.– Judge an individual resume.

Page 5: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

System design: components

Facts generation

Run CLIPS

Explanation1

2

3

Page 6: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

Step 3-1 Generate facts

wxPython and Python

Beautifulsoup, NLTK and Python

Page 7: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

Step 3-2 Run CLIPS

Python and PyCLIPS

Page 8: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

Step 3-3 Explanation

Python and wxPython

Page 9: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

Milestones

• Jon S. part goes from here

Page 10: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

Meetings with experts

• Max and Jon M. part goes here

Page 11: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

Work divisions (pls edit based on your needs:))

• Individual accomplishment:– Max and Jon M:– Jon S.:– Wei: resume formatting, resume parsing, resume CLIPS facts

generation. • Shared accomplishments:

– Discussion on the overall design of the system.– Preparation of knowledge base.– Discussion on facts structure and inference rules.– Discussion on scoring strategy and explanation system.– Timebox, deliverables, expert contact and group meetings.

Page 12: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

Bolts and Nuts Part 3-1

Resume parsing and facts generation

Page 13: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

NLTK and Beautifulsoup

• NLTK (natural language toolkit) is used to extract resume facts based on linguistic patterns.– “(I) Worked on Ruby on Rails application creating

matching algorithms and UPC database.”– I/PRP worked/VBD on/IN Ruby/NNP on/IN Rails/JJ

application/NN creating/VBG matching/VBG algorithms/NNS and/CC UPC/NN database/NN ./.

• Beautifulsoup, a python library handling DOM objects.

Page 14: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

HTML resume to CLIPS facts

HTML resume

Experience

Position Leadership quality

Experience description Work area quality

Duration Loyalty quality

Skills Skill qualities

Certifications Certification qualities

Education

DegreeDegree quality

School School rank quality

Major Major quality

DOM root

DOM objects

Text area and attributes of objects

Page 15: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

HTML structure

……<div id="company1" title="ClearNet Security"> <div id="position11">Consultant</div> <div id="exp_time11">January 2010-April

2010</div> <div id="experience11">Worked on Ruby on Rails

application creating matching algorithms and UPC database.</div>

</div>……

Page 16: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

Deftemplates for these facts are predefined.

Page 17: ERecruiter Expert System Presenters: Date. Agenda Review (Wei 2 mins) – Problem domain – Overview of the system Milestones (Jon S. 2 mins) – Timeboxes

Coding convention

• Resume facts CLIPS file is named uniquely as ID_Name.clp.

• Each deffacts has a ID slot to uniquely identify a candidate.