Learn More
In order for robots to effectively understand natural language commands, they must be able to acquire meaning representations that can be mapped to perceptual features in the external world. Previous approaches to learning these grounded meaning representations require detailed annotations at training time. In this paper, we present an approach to grounded(More)
Our goal is to improve the efficiency and effectiveness of natural language communication between humans and robots. Human language is frequently ambiguous, and a robot's limited sensing makes complete understanding of a statement even more difficult. To address these challenges, we describe an approach for enabling a robot to engage in clarifying dialog(More)
—Our goal is to build robots that can robustly interact with humans using natural language. This problem is challenging because human language is filled with ambiguity, and furthermore, due to limitations in sensing, the robot's perception of its environment might be much more limited than that of its human partner. To enable a robot to recover from a(More)
When designing a distributed network protocol, typically it is infeasible to fully define the target network where the protocol is intended to be used. It is therefore natural to ask: How faithfully do protocol designers really need to understand the networks they design for? What are the important signals that endpoints should listen to? How can(More)
  • Amy Ousterhout, Li Braries, Hari Balakrishnan, Fujitsu Chair, Rofessor, Leslie A Kolodziejski +8 others
  • 2016
Network resource management schemes can significantly improve the performance of datacenter applications. However, it is difficult to experiment with and evaluate these schemes today because they require modifications to hardware routers. To address this we introduce Flexplane, a programmable network data plane for datacenters. Flexplane enables users to(More)
  • Citation Sivaraman, Keith Anirudh, Pratiksha Winstein, Hari Thanker, Balakrishnan, An +4 others
  • 2014
The MIT Faculty has made this article openly available. Please share how this access benefits you. Your story matters. ABSTRACT When designing a distributed network protocol, typically it is in-feasible to fully define the target network where the protocol is intended to be used. It is therefore natural to ask: How faithfully do protocol designers really(More)
  • Citation Tellex, Pratiksha Stefanie, Joshua Thaker, Nicholas Roy Joseph, Springer-Verlag, Stefanie Tellex +3 others
  • 2013
Learning perceptually grounded word meanings from unaligned parallel data. The MIT Faculty has made this article openly available. Please share how this access benefits you. Your story matters. Abstract In order for robots to effectively understand natural language commands , they must be able to acquire meaning representations that can be mapped to(More)
The second moment method is the study of the use of variance, and in particular Chebyshev's inequality. It can be used to show that when the expected value of a nonnegative random variable is large compared to its variance, it takes on the value zero with probability approaching zero. Or, said differently, it can be used to show that a random variable has a(More)
In order for robots to effectively understand natural language commands, they must be able to acquire a large vocabulary of meaning representations that can be mapped to perceptual features in the external world. Previous approaches to learning these grounded meaning representations require detailed annotations at training time. In this paper, we present an(More)
  • 1