Founding father of BYOR - AI WITH THE BEST 2016
AI Together with the Best will be the biggest online conference for data scientist, developers, tech teams and startups happening the 24th & 25th September 2016 giving you 100 incredible speakers by having a novel, online conference platform. Meet Aerin Kim, Data Scientist turned Founder of startup BYOR (Create your Own Resume) speaking at AI Together with the Best, online tech conference about her Phrase2Vec technology. Aerin is building an AI-based resume helper using NLP parsing. Every time a user uploads her resume for the webapp, it gives suggestions on how to increase your resume regarding its wording or phrases.
Please reveal a bit about your background ahead of BYOR and just how have you end up in data?
I became a NLP data scientist at the startup called Boxfish. I did so a lot of Twitter text modeling there coupled with been fascinated every day with the quantity of information that may be gleaned from all of the words that individuals were generating. Given it would have been a startup, our company was building the product or service yourself over many iterations. That training solved the problem later while i turned my idea into a product (BYOR).
What propelled that you push NLP parsing technology for Resumés?
My co-founder and that i have been volunteering as resume reviewers and mentors for Columbia University since 2014. Each year, we found there's a pattern for weak resumes and now we found ourselves giving students the identical advice year after year. We were treated to a way for some automation with this resume reviewing process.
Also in school career centers, it’s challenging a one-on-one session with career advisors since the student-to-advisor ratio is hundreds to a single. We thought we would develop a tool that could be utilised by students to check their resume before meeting their career advisors, or as an alternative.
The BYOR project started since the class problem for the CS 224d (Dr. Richard Socher) at Stanford. Rohit and I took that class online.
How can you train the word embedding neural networks to get similarities and relations between phrases?
The principle option to finding similarities and relations between two different phrases is converting these phones phrase vectors then finding the distance between these vectors. There are various solutions to calculate phrase vectors. The best way that you can try is to first train the word vectors then weight average those word vectors found in the phrases.
So what can BYOR do compared to other CV checkers?
Currently, there isn't any company that suggests result phrases over a specific sentence. Even AI companies with good volume of funding don’t open their platforms like us. Inviting people to upload just about any resume and provides them suggestions can be a challenging problem on many levels and taking it on requires a little bravery.
What traditional CV checkers do is easy keyword extraction or keyword counting to check whether certain test is used or otherwise. They don’t see the user’s resume line by line semantically.
What’s been probably the most exciting portion of your startup adventure?
Essentially the most exciting part is the place we help the “phrase suggestion algorithm” day by day and achieve generating phrases that produce sense.
Also, before the startup, That i used to help a huge bank. If you are an employee of a giant company, your task description is very narrowly focused. But in a startup, I will research all parts in the product. It is often exciting to me so far.
Also, it’s amazing to determine a lot of people contributing to BYOR voluntarily.
If it’s not a secret, that is your favourite technological setup?
It’s not a secret. We use python django for web. All NLP/deep learning code is written in python.
To train word vectors, we use code developed in C.
What advice would you give to budding AI developers?
In case you are AI developer, Applied Math basics are necessary in your case. Invest a few of your time and energy go over Linear Algebra, Optimization, Probability which you learned during college.
Have you been pumped up about speaking at AI Using the Best?
Yes! I love that it’s priced under 100 bucks to ensure average man or woman can attend. And it’s on the internet!!! People/students shouldn’t have to have sponsors to visit such tech conferences. Using the Best line-up will be as good like a $3000 conference.