I am interested in the development, improvement, and analysis of machine learning methods with a focus on systems that can aid in the automatic analysis of natural language as components of adaptive systems or information retrieval systems. My current focus is on contextually intelligent assistants. I also maintain an active interest in contextual and personalized search, enriched information retrieval, active sampling and learning, hierarchical and large-scale classification, and human computation and preferences.
My past work has examined a variety of areas — primarily ensemble methods, calibrating classifiers, search query classification and characterization, and redundancy and diversity, but also extending to transfer learning, machine translation, recommender systems, and knowledge bases.
In addition to my research, I engage in a variety of professional service activities for the machine learning, data mining, and information retrieval…. Bennett brings us up to speed on the science of contextually intelligent assistants, explains how what we think our machines can do actually shapes what we expect them to do, and shares how current research in machine learning and data science is helping machines reason on our behalf in the quest to help us find the right information effortlessly.
Follow us:. Share this page:. In addition to my research, I engage in a variety of professional service activities for the machine learning, data mining, and information retrieval… Read more. Featured content. And so, you know, we think about how do we construct guarantees on privacy between our different customers that prevents anything from going in-between, right? Even indirectly. And so, yes, absolutely, the first thing we do is say, you know, we will limit ourselves in terms of the predictive capabilities to make sure that we guarantee that first.
Host: Which is an interesting promise and perspective. So how can you educate users, customers, etc. Paul Bennett: You know, I think we just have to, first off, keep communicating that, but also just be true to our word not just in what we do, but in who we partner with, you know?
We work with a lot of external partners. We ask our partners, how are you working with your data? Who would agree to this? Was this a broad enough agreement? Host: Tell us a bit about Paul Bennett. Paul Bennett: I started quite a while ago. Originally looking first at just philosophical problems of how we reason about things.
And I started uh…. Paul Bennett: Not that long ago! But going back to undergrad. And I was actually looking about how do people reason about court cases. So, I not only did philosophy, it was more from the theorem proving side, the logical side of things. And so, in undergrad, I did both a philosophy and a computer science degree where I looked more at the computer science side, again, of doing this.
And, you know, the computer science part of the project I mentioned was to actually build this recommender system as well on the computer science part of things. But more generally, as I got deeper and deeper into AI, it was seeing how AI could really transform situations and moments. I typed in English and I got French out.
Which was interesting. And I was actually sitting in an international conference in Finland at the time and because it was an international conference there were a number of people around, and I raised my hand and I said, does anybody speak French here? Somebody said yes. And I walked over to them and said…. Paul Bennett: I walked over to them and said, does this French sentence say what the English sentence says?
And they said yes. And then I typed another one. Does this say the same thing? They said yes. And I did another sentence. And that is simply magical. During my time in grad school at Carnegie Mellon, I actually came out as an intern.
And so, you know, if you are an undergrad or a graduate student listening, internships are a hugely important part of your career development. At the time, I was looking at how do we actually ensembles of machine learning methods. That gave me an opportunity to start engaging with them and then, you know, when I went back to Carnegie Mellon, I continued to engage with them throughout the time of my dissertation.
And then after I was finished with grad school, I came out and started as a researcher. And so, they started actually bringing in other disciplines at the time and saying, what happens if we put people together from different disciplines, how would it apply to this portion of the world? Host: I like to ask all my guests, when we come to the end of our conversation, to offer some parting thoughts to our listeners.
How might some of the brightest minds think about joining the efforts in this area, Paul? Paul Bennett: I think there are a number of different ways that people can contribute. You know, what are the opportunities? Something that you look at and you say, this is not an opportunity for computing.
How would you turn it into an opportunity? Where is the current friction? You know, I even think about the simple things like during undergrad I worked for the government for a while. We had these forms.
Everything had to be on an official form. And one of my great innovations at the time was I created templates where you could photocopy onto these official forms most of the things that you needed for each person in the office.
And that, again, was just an example of the computing mindset, right? And that can happen in any field, regardless of what you work in, regardless of whether you are in AI or not.
Host: Paul Bennett, saving time and changing outcomes. Thanks for coming on the podcast today. To learn more about Dr. Paul Bennett and how researchers are building contextually intelligent assistants to deliver contextually intelligent assistance, visit Microsoft. Follow us:. Share this page:. Building contextually intelligent assistants with Dr. Research Area Artificial intelligence Data platforms and analytics Systems and networking. Paul Bennett: Thank you. Host: Right. Host: So, how are you doing that?
Host: And, which email from Paul is the one I remember? And so, I made it efficient for you to identify that, right? Host: Sure. I mean, is it Radar-esque for you now? Those come up across the whole different suite of… Host: What about other verticals like education or you know these other big chunks, healthcare, etc.? And I started uh… Host: Was this when you were a child? How far back are we going? And I walked over to them and said… Host: Did they say yes or oui?
Host: So, how did you end up here? Host: Who did you work with? Host: Carnegie Mellon. It seems like an incubator for MSR in a lot of ways. Paul Bennett: Thank you Gretchen.
0コメント