Author Archives: articulab

A Summer in the Land of WoZ

Well that’s a wrap! I am officially done with my internship. Crazy to think that I have been here for two and a half months! With it being my final week it was my turn to present the work I completed this summer to everyone in the lab meeting.

I have always enjoyed making presentations. Presentations allow me to better gage how much I know and how much I learned throughout a process. With this presentation, it was rewarding to see that I accomplished my goal of being fully engaged in a research project and pushing myself to learn the in and outs of different experimental designs. While preparing for this presentation, I categorized everything I did this summer into three categories:

  • Explored the Wizard-of-Oz experiment design space and prior work in the field
  • Designed a custom Wizard-of-Oz Graphical User Interface
  • Programmed a Wizard-of-Oz Graphical User Interface

By categorizing, I realized I did not fully get everything done that I wanted to with number three. I kept having new ideas of improvements I could do for the program that I ran out of time to implement. I mentioned this disappointment to my lab advisor and he told me something I never thought before. He said that he hoped that I was not fully content with my work. He said that noticing there is still improvements to be done, but not enough time to get them done reveals that one was invested in his or her work.  And with that comment, I was content with all the work I finished this summer.

If you are a Dickinson student that is pursuing a low paying or nonpaid internship be sure to apply to the Summer Internship Grant. It provides students the opportunity to pursue these internships by providing funds to cover expenses such as housing, food, transportation, and parking. I would not have been able to accept this internship without the help of the Dickinson Internship fund! So thank you again Dickinson!

It has been a fun journey, but I am officially over and out! Thanks for following my internship blog this summer.

Always Learning

As everyone says, “An internship is a great learning experience”. It is true. I learned more about the field, what my interests are, and where my strengths and weaknesses lie throughout this entire experience.

With the end of summer coming fast, I felt it would be nice to make a small list of some of what I have learned this summer. So without further ado, here is a brief list of some of what I have learned.

1.Always be prepared for whats next, but commit yourself for the present

In the field of human-computer interactions and design, there are a limitless number of possibilities. However, there is also a limited amount of time. Being able to commit yourself to a  a few designs to meet deadlines while planning ahead for possible fixes and alterations that can address possible questions and changes in the development cycle is necessary for success.

2. Artificial Intelligence is not going to take over the world

Working in a lab that focuses on making artificial intelligence with compassion and the best traits of what humans possess (rapport, curiosity) has shown me that A.I is not going to take over the world.

3. Always Question

Having the opportunity to go to talks and presentations while doing research at Carnegie Mellon has been a great experience. The one thing always present at these presentations was a continuous amount of questions. Some of the questions can seem quite “harsh” with direct remarks of what did not work or did not make sense in the presentation. These direct, difficult questions are never perceived here as harsh at Carnegie Mellon. Instead they act as a point of continuous conversation that result in great mutual development between the speaker and the audience.

4. Spend time Debriefing

Taking time directly after a meeting to review your notes from the meeting and coming up with what your main take away from the meeting are is crucial! Always be planning your next steps.

 

Summer is Coming to a Close…

My apologies for not posting in a while. The past two weeks have been a whirl-wind of busy! Team meetings, wrapping up projects, and preparing for presentations have been my main priorities these final weeks. On top of this, I have still been doing landscaping on the side and keeping up with my swimming training! This definitely has been a summer to remember and I am excited to see my work come full circle.

Our weekly lab meetings, which includes all members in the lab from undergraduates to postdocs, now has wrap-up intern presentations. These presentations are given by leaving interns about the work they completed during their internship. A highlight about working at ArticuLab as an intern is that each intern is working on his or her own separate project. An intern is assigned an assignment at the start of their internship and given free-reign to figure out how best to finish the assignment.

It definitely is a lot to take in at the beginning. Here you are with new software, new computer languages, new toolkits, and a new computer architecture to learn before even being able to think about tackling your main assignment. However, this freedom is what makes the internship. It provided me with the skills and confidence to know that I can be thrown into a completely new environment, learn all that I need to, and then create a plan on how to finish the assignment. This freedom is what makes seeing my end work so rewarding. I can still remember how I had no idea what a Wizard-of-Oz experiment even was, but now I can tell you about this entire field of research.

Watching my fellow interns present their work is in a cliché way inspiring. I know first-hand by working with them the struggles and frustrations that they have faced while completing their work. To see projects such as new automatic head nod-tracking software being presented and demonstrated by my fellow interns is really incredible. Being a part of this internship revealed to every intern what they truly are capable of making.

Diversity

One of the best parts of interning at ArticuLab this summer been the diversity of the staff both in culture and disciplines. My fellow interns come from all over: India, China, France, Texas. I am one of the few summer interns that is from Pennsylvania! This diversity from where we come from has allowed for a continuous flow of unique and different ideas and thought processes. I never thought when coming to this internship I would learn as much as I have about different cultures. From going out to dinner to exploring nearby parks, I have learned just as much from the conversations in the lab to the ones outside work.

On top of this mixing of so many different cultures, the interdisciplinary of the research being done provides further to the diversity. My favorite part of Dickinson is the interdisciplinary approach to education. I am able to take classes based on all my interests from computer science to environmental studies. Working in an actual lab that fully supports and encourages interdisciplinary research has been amazing. I have gotten to interact with professionals in Computer Science, Machine Learning, Linguistics, Psychology, and Human-Computer Interactions. Working in this lab has revealed further the power of a liberal arts education.

My time at ArticuLab is quickly coming to a close. I only have two weeks of work left! Thanks again to the Dickinson Internship Grant for providing me the funds to be able to pursue this experience!

To close out this post, here is a picture of me and my fellow ArticuLab Summer Interns!

13730919_1062534193782591_1099539325292827216_o

 

Inspiration from The Wizard of Oz

One of the great unexpected twists from the classic movie, The Wizard of Oz, as a child was the revealing of the Wizard not being some magnificent god. Instead he was just a plumped, normal human. This deceiving act is the inspiration of an experimental set up used in human-computer interaction research: A Wizard of Oz Experiment or WoZ for short.

A difficult aspect in this field’s research is the time-intensive and expensive nature of creating and programming new software and algorithms.  Many researchers in the field start with a hypothesis such as: a virtual assistant that can develop rapport with a human is more effective in aiding humans with their tasks than a a virtual assistant that does not develop rapport with a human such as Siri, Cortana, Google Now etc. To best verify this hypothesis, a virtual assistant would be built that can develop rapport. Then this rapport-building virtual assistant would be tested on humans to see if it more beneficial compared to a current virtual assistant by using a measured and controlled test.

This process seems straight forward until lets say that the tests reveal that the rapport building virtual assistant is not more effective in aiding humans with tasks than the normal virtual assistant. Now all this time, energy, and money has gone to waste into developing this brand new, never done before virtual assistance that is not more useful than older technology.

This is why WoZs are use! A WoZ experiment starts with telling a human that a computer program is fully autonomous while in reality a human in another room is controlling what the computer is doing. So in this example, instead of creating a automated rapport and dialogue selection system, all that is created is a user interface that a human called a Wizard can control to make it seem that this virtual assistant that is developing rapport is fully autonomous. This way is much cheaper and quicker than the prior description. If the hypothesis gets verified, then the actual automated computer software is created. A WoZ can be used throughout the design process by slowly getting rid of the scope of control that the Wizard has over the virtual assistant until the Wizard is no longer needed!

It is such a simple concept, but the benefits of it are huge! Instead of starting right away building technology that might not be useful, a person first tests a human (Wizard) controlled scenario that mimics what the computer would do without the subject knowing. If it proves effective, then the actual, autonomous software is programmed and created!

My main job at ArticuLab has been researching past and present WoZ design philosophy/systems and creating a WoZ interface to use on a lab project. Having the ability to learn and experiment with different techniques such as utilizing a WoZ has really helped me understand the wide variety of ways researchers conduct their research.

 

*** ArticuLab’s work on this hypothesis can be found here: SARA

Mastering the Elevator Pitch

The project I am apart of at ArticuLab this summer is the Rapport-Aligning Peer Tutoring (RAPT) project. This week in our staff meeting we had to prepare and present an “elevator pitch” to everyone in the lab. An elevator pitch is an under 30 second speech trying to sell your research.

So the scenario goes: You are at a research conference and lets say you enter an elevator with Bill Gates. You have only five floors to make your case to him on why your research is so important and to spark his interest. This interest should hopefully lead to funding for your research.

With elevator speeches, you are trying to sell your research. Therefore, a great source for inspiration are infomercials. An elevator pitch should not be wordy or complicated by tons of technical terms. Instead, it should spark interest in the listener. As a researcher, funding is crucial to any project and the more you understand how to sell your work in a manner that reveals its importance to a person outside the field, the more likely you will receive the funds you need.

Below is a small example of an elevator pitch I came up with for the RAPT – the project I am working on:

Education disparities between the poor and rich is a real problem. Tutoring should be an avenue to help close this gap, however, the cost of tutoring have made it an avenue only for the rich. What if I told you we could provide highly-effective, low cost, maybe even free, tutoring to all? My research focuses on creating a virtual tutor that can develop meaningful conversation with its student. Meaningful conversation or rapport is crucial to effective tutoring. It is our goal to create an effective, rapport-building virtual tutor which could act as a key to helping to eliminate educational disparities.

Finding Research

Going on the hunt to find an internship, I knew I wanted one that involved research. I never experienced research before so I wanted to experience it to determine if it was a career path I would be interested in pursuing. I tried many strategies when trying to find this internship such as contacting family friends in the field to exploring different professor’s websites to see if they have any research intern positions open.

How I ultimately found ArticuLab was unexpected. Since I have an interest in technology and human computer interactions I follow a handful of different blogs that report about advances in the field. One of the posts was a TedxPittsburgh video of a professor named Justine Cassell talking about integrating robots and virtual peers into society. I decided to go to her website to read about her research. This led me to her lab at Carnegie Mellon: ArticuLab.

Being a native of Pittsburgh, I realized this lab was not far from my house. Getting a research position there would be perfect. However, no positions were being advertised currently on the lab’s website. I decided to take a chance and forward a cover letter and resume to the lab manager detailing my interests in the lab’s work and what I could contribute if I had an opportunity to work in the lab over the summer. Within a week I was Skyped interviewed and offered a summer intern position.

Through this internship hunt, I learned that if you find a company or lab that you feel a connection to but no positions are advertise, still initiate the conversation. The worst that can come from it is a response saying no positions are available.

Bio

I’m Offical

I am finally official! My bio was just posted on the lab’s website if anyone would like to check it out (click here). It was last week when I first started my internship and before coming into the lab to start I received a few scholarly articles from my adviser to read.  They discussed the lab’s work on creating a computer architecture for developing and building rapport. Being prepared and reading additional articles written by the lab before starting definitely helped make the transition in the first few days smoother.

With having no prior experience working in a research lab setting, I was not exactly sure what to expect. All I knew coming in was that I was going to be working on the lab’s Rapport-Aligning Peer Tutor (RAPT). Having been in the lab for six days now, I can say that this might be some of the most hard working and dedicated people I have worked with. Their work-ethic and love for the research they are conducting is shown through their dedicated focus, passion, and long hours they spend in the lab. Having the opportunity to watch and work with such a group is motivating. The lab is currently working around the clock to prepare for an exhibition of their Yahoo!-CMU InMind project at the World Economic Forum in China in the coming weeks. A very unique and captivating project that I have had the opportunity to test!

I am excited to see all that I will experience and learn over the summer from working at ArticuLab. Next week I will dive more into the project I am working on!