Nathaniel Weir Wins The Randy F. Pausch Computer Science Undergraduate Summer Research Award
- Posted by Jesse Polhemus
- on May 21, 2018
Click the links that follow for more news items about Carsten Binnig, Ugur Çetintemel, Peter Norvig, and the Randy F. Pausch '82 Computer Science Undergraduate Summer Research Award.
The Randy F. Pausch '82 Computer Science Undergraduate Summer Research Award, given this year to Nathaniel Weir to support his work with Professor and Department Chair Ugur Çetintemel, recognizes strong achievement from young students and offers them the opportunity to partner with faculty and advance work that began in the Brown CS undergraduate research program.
A generous gift from Peter Norvig '78 (a Director of Research at Google and a thought leader in the areas of artificial intelligence, natural language processing, information retrieval, and software engineering) established the award, which provides $10,000 annually to support an undergraduate engaged in an intensive faculty-student summer research partnership. The gift honors the life and work of Randy F. Pausch '82, a renowned expert in computer science, human-computer interaction, and design who died of complications from pancreatic cancer in 2008. "His story is inspiring," Peter says, "and this is an opportunity to remember him."
Nathaniel's project, he explains, explores a deep learning approach to Natural Language Interfaces for Databases (NLIDBs). "We're building a user-friendly interface," he says, "for interaction with a relational database management system (RDBMS) without requiring prior knowledge of SQL or the specifics of database schemas. It should be able to respond to any natural language query of the database with the proper table of requested information. Our project attempts to solve a number of current challenges of pertinence to the database and natural language processing communities. These include database independence, vocabulary robustness, stateful conversationality, and the ability to respond to complicated or comprehensive requests that involve difficult database operations or multi-level nested queries."
"It feels amazing to be recognized for this kind of work," Nathaniel says. "Natural language understanding is one of the coolest new areas of deep learning, and I'm extremely grateful to be a part of the team pushing the initiative at Brown. Working with Carsten and Ugur has been really interesting – our weekly group meetings are always full of new ideas and debate, and I'm lucky even to be able to sit in on them, let alone contribute to them in a meaningful way."
Currently, their system implements a novel sequence-to-sequence deep model to translate natural language utterances into SQL, with performance comparable to other state-of-the-art NLIDBs. The next steps will be to further extend its capabilities. Possible avenues include adding more query templates for more functionality, using off-the-shelf dependency parsers, automatically recognizing nested queries and translating them independently, and expanding automatic paraphrasing using Paraphrase Database (PPDB).
"I'm incredibly happy to have the opportunity to continue working on this project," says Nathaniel, "I'm very excited by challenges that use the capabilities of artificial intelligence to guide the process of human research: building a system that automates the process of receiving insights from databases is a perfect example of such a project. It's also given me the chance to explore the behavior of deep learning models in a hands-on way. A lot of the first obstacles in the process of getting the system up and running have already been passed in the last year – now I'm really excited to start tackling more complicated tasks. It's great that we already have a system performing to the level that it does, but knowing that there are ways to make it even more capable is really exciting."
That sort of excitement is exactly what Peter Norvig is looking for. He sees this award as a "multiplier" that will amplify the value of his gift and extend it through time. "In the past," he says, "we had to build all our own tools, and we didn't have time to combine computer science with other fields. Now, there are so many opportunities to do so. I think it's a wise choice: you invest in things that you think will do good, and educating a student allows them to help add to the things that you're already trying to accomplish."
For more information, click the link that follows to contact Brown CS Communication Outreach Specialist Jesse C. Polhemus.