Pingar is a text analytics company. Our awesome technology extracts information from unstructured text and makes it available to customers via user-friendly interfaces. Out product, DiscoveryOne provides solutions for Content Enrichment and Content Inventory.
The project: “Build models for text classification”
Text classification (also known as text categorization) is an important component of Pingar’s DiscoveryOne. The need to categorize documents based on their content (politics, sport, entertainment, science…) or their type (agenda, manual, contract…) is important to most businesses and therefore to most of our customers.
Our team has developed a set of tools for building computer models that automatically recognize in which category to put a new, never seen before, electronic document. We have rule-based (when the terminology is specialized and defined), machine learning (where a large number of documents is used for learning a classifier) and hybrid models.
You will build a few such models using training data.
You will learn about text mining, machine learning and enterprise information management.
Project commences: 1 Dec 2017 (flexible)
Contract remuneration: $7,200 for 400hrs
According to: https://www.callaghaninnovation.govt.nz/student-grants/rd-experience-grants to be eligible for an R&D Experience Grant placement, students must:
– Have completed their first year of an undergraduate or honors degree, a postgraduate diploma or certificate, or co-joint undergraduate degrees. If graduated, this must have been in the last 12 months.
– Be studying science, technology, engineering, design or business at a New Zealand tertiary education institute.
– Be a New Zealand citizen or resident or hold a relevant visa.
– Not have been previously employed at the business.
– Not have been previously employed in the industry under a professional arrangement unless temporary (up to 3 months).
The above criteria are STRICT. We will only respond to eligible candidates.
Additionally, Pingar would like:
– Good programming skills in Java or C#
– Interest in business information
– Interest in machine learning
– Knowledge of databases, semantic technologies, and interest in data mining would be an advantage.
We have some flexibility on the start date but ideally, we would like the intern to start sometime between 1st of Nov 2017 and 10th of Jan 2018. The project is for 400 hours (10 weeks full time).
To apply or to get more information, email us at firstname.lastname@example.org
Use subject line: Callaghan Innovation Experience Internship
For applications, email your CV and a brief cover letter.
Please make sure you are eligible based on the Callaghan Innovation criteria! We will only respond to eligible candidates.