FOUNDER OF BYOR - AI WITH THE BEST 2016
AI With The Best is the biggest online conference for data scientist, developers, tech teams and startups happening the 24th & 25th September 2016 providing you with 100 incredible speakers via a novel, online conference platform. Meet Aerin Kim, Data Scientist turned Founder of startup BYOR (Create your Own Resume) speaking at AI Using the Best, online tech conference about her Phrase2Vec technology. Aerin is building an AI-based resume helper using NLP parsing. Whenever a user uploads her resume for the webapp, it gives suggestions on the way to improve your resume regarding its wording or phrases.
Please reveal a little about your background just before BYOR and just how did you get into data?
I became a NLP data scientist at a startup called Boxfish. Used to do plenty of Twitter text modeling there together been fascinated every single day with the amount of information that may be gleaned from all of the written text that folks were generating. Since it was a startup, all of us was building the product or service from scratch over many iterations. That training reduced the problem later after i turned my idea in a product (BYOR).
What propelled one to push NLP parsing technology for Resumés?
My co-founder and I have already been volunteering as resume reviewers and mentors for Columbia University since 2014. Every year, we found there exists a pattern for weak resumes and we found ourselves giving students the identical advice year after year. We had an opportunity for some automation on this resume reviewing process.
Also in school career centers, it’s hard to get a one-on-one session with career advisors because the student-to-advisor ratio is hundreds to one. We made a decision to create a tool that might be utilised by students to check their resume ahead of meeting their career advisors, or as an alternative.
The BYOR project started since the class work for the CS 224d (Dr. Richard Socher) at Stanford. Rohit and i also took that class online.
How do you train the word embedding neural networks to discover similarities and relations between phrases?
The main way to find similarities and relations between two different phrases is converting the crooks to phrase vectors after which choosing the distance between these vectors. There are various approaches to calculate phrase vectors. The most effective way that anyone can try is always to first train the phrase vectors and then weight average those word vectors employed in the phrases.
So what can BYOR do in comparison to other CV checkers?
Currently, there isn't any company that implies result phrases on a specific sentence. Even AI companies with good quantity of funding don’t open their platforms like us. Inviting visitors to upload any kind of resume and provides them suggestions can be a challenging problem on many levels and taking it on uses a little bravery.
What traditional CV checkers do is easy keyword extraction or keyword counting to test whether certain language is used or otherwise. They don’t comprehend the user’s resume line by line semantically.
What’s been essentially the most exciting part of your startup adventure?
Essentially the most exciting part is when we improve the “phrase suggestion algorithm” daily and succeed in generating phrases that make sense.
Also, before the startup, I did previously work for a major bank. An advanced employee of a big company, your job description is very narrowly focused. However in a startup, I will test out every aspect with the product. It has been extreme fun for me personally up to now.
Also, it’s amazing to determine many individuals causing BYOR voluntarily.
If it’s not a secret, that's your favourite technological setup?
It’s a well known fact. We use python django for web. All NLP/deep learning code is written in python.
To practice word vectors, we use code coded in C.
What advice do you share with budding AI developers?
If you're AI developer, Applied Math basics are essential for you. Invest a few of your time go over Linear Algebra, Optimization, Probability that you just learned during college.
Are you pumped up about speaking at AI With all the Best?
Yes! I love that it’s priced under 100 bucks to ensure that public can attend. And it’s on the internet!!! People/students shouldn’t require sponsors to wait such tech conferences. With The Best line-up is really as good as being a $3000 conference.