Founding father of BYOR - AI WITH THE BEST 2016
AI Using the Best will be the biggest online conference for data scientist, developers, tech teams and startups happening the 24th & 25th September 2016 presenting to you 100 incredible speakers through a novel, online conference platform. Meet Aerin Kim, Data Scientist turned Founder of startup BYOR (Build Your Own Resume) speaking at AI With all the Best, online tech conference about her Phrase2Vec technology. Aerin is building an AI-based resume helper using NLP parsing. Each time a user uploads her resume for the webapp, it gives suggestions on the way to improve your resume regarding its wording or phrases.
Please tell us a bit about your background prior to BYOR and the way would you get into data?
I had been a NLP data scientist with a startup called Boxfish. I did a great deal of Twitter text modeling there together been fascinated daily from the volume of information that may be gleaned coming from all the text that people were generating. Because it would have been a startup, our company was building the merchandise yourself over many iterations. That training solved the problem later while i turned my idea in 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. Yearly, we found there exists a pattern for weak resumes and now we found ourselves giving students the identical advice every year. We were treated to a way for some automation on this resume reviewing process.
Also at college career centers, it’s challenging to get a one-on-one session with career advisors as the student-to-advisor ratio is hundreds to a single. We thought we would create a tool that might be employed by students to analyze their resume ahead of meeting their career advisors, or alternatively.
The BYOR project started since the class project for the CS 224d (Dr. Richard Socher) at Stanford. Rohit and that i took that class online.
How would you train the word embedding neural networks to find similarities and relations between phrases?
The primary approach to finding similarities and relations between two different phrases is converting them to phrase vectors after which finding the distance between these vectors. There are several ways to calculate phrase vectors. The best way that one can try is usually to first train the phrase vectors and after that weight average those word vectors utilized in the phrases.
So what can BYOR do in comparison with other CV checkers?
Currently, there is absolutely no company that suggests result phrases over a specific sentence. Even AI companies with higher level of funding don’t open their platforms like us. Inviting visitors to upload just about any resume and present 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 check on 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 a part of your startup adventure?
The most exciting part is the place we increase the “phrase suggestion algorithm” day-to-day and reach your goals in generating phrases that make sense.
Also, prior to the startup, I did previously benefit a huge bank. If you are a employee of a big company, your job description is very narrowly focused. But in a startup, I will test out every part from the product. Many experts have extreme fun for me thus far.
Also, it’s amazing to view many people leading to BYOR voluntarily.
If it’s a well known fact, which is your favourite technological setup?
It’s not a secret. We use python django for web. All NLP/deep learning code is constructed in python.
To practice word vectors, we use code designed in C.
What advice can you share with budding AI developers?
If you are AI developer, Applied Math basics are very important in your case. Invest a few of your time and effort to talk about Linear Algebra, Optimization, Probability which you learned during college.
Are you looking forward to speaking at AI Together with the Best?
Yes! I like that it’s priced under 100 bucks to ensure that public can attend. And it’s on the net!!! People/students shouldn’t require sponsors to visit such tech conferences. Using the Best line-up is as good as being a $3000 conference.