Founding father of BYOR - AI Together with the BEST 2016
AI With 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 Founding father of startup BYOR (Make 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. When a user uploads her resume on the webapp, it offers suggestions regarding how to enhance your resume regarding its wording or phrases.
Please inform us a little about your background before BYOR and exactly how do you enter data?
I had been a NLP data scientist at the startup called Boxfish. Used to a lot of Twitter text modeling there along been fascinated daily by the level of information that is gleaned from all the text that people were generating. As it would have been a startup, we was building the merchandise from scratch over many iterations. That training taught me to be later after i turned my idea in a product (BYOR).
What propelled that you push NLP parsing technology for Resumés?
My co-founder and that i happen to be volunteering as resume reviewers and mentors for Columbia University since 2014. Each year, we found there exists a pattern for weak resumes and that we found ourselves giving students the same advice year after year. We saw a chance for some automation in this resume reviewing process.
Also at college career centers, it’s hard to get a one-on-one session with career advisors for the reason that student-to-advisor ratio is hundreds to at least one. We chose to build a tool that may be employed by students to analyze their resume before meeting their career advisors, or instead.
The BYOR project started as the class work for the CS 224d (Dr. Richard Socher) at Stanford. Rohit and that i took that class online.
How would you train the phrase embedding neural networks to discover similarities and relations between phrases?
The principle strategy for finding similarities and relations between two different phrases is converting the crooks to phrase vectors then locating the distance between these vectors. There are many different methods to calculate phrase vectors. The easiest way that you can try would be to first train the term vectors and after that weight average those word vectors utilized in the phrases.
So what can BYOR do compared to other CV checkers?
Currently, there is absolutely no company that suggests result phrases on a specific sentence. Even AI companies with higher amount of funding don’t open their platforms like us. Inviting website visitors to upload any type of resume and give them suggestions is really a challenging problem on many levels and taking it on requires a little bravery.
What traditional CV checkers do is straightforward keyword extraction or keyword counting to evaluate whether certain words are used you aren't. They don’t comprehend the user’s resume line by line semantically.
What’s been the most exciting a part of your startup adventure?
Probably the most exciting part is the place we increase the “phrase suggestion algorithm” day-to-day and achieve generating phrases that produce sense.
Also, prior to the startup, I did previously work with a major bank. An advanced employee of a big company, your work description is incredibly narrowly focused. In a startup, I'm able to try out every part with the product. Many experts have thrilling for me personally so far.
Also, it’s amazing to view lots of people adding to BYOR voluntarily.
If it’s a well known fact, which can be 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 teach word vectors, we use code developed in C.
What advice do you get for budding AI developers?
In case you are AI developer, Applied Math basics are important for you. Invest a number of your time and effort to talk about Linear Algebra, Optimization, Probability which you learned during college.
Have you been pumped up about speaking at AI Together with the Best?
Yes! I favor that it’s priced under 100 bucks so that general 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.