Benchmarking Generalization via In-Context Instructions on 1, 600+ Language Tasks
- Yizhong Wang, Swaroop Mishra, Daniel Khashabi
- Computer ScienceArXiv
- 2022
This work introduces N ATURAL -I NSTRUCTIONS v 2, a collection of 1,600+ diverse language tasks and their expert written instructions that covers 70+ distinct task types, such as tagging, in-filling, and rewriting.
i-Vectors in speech processing applications: a survey
- Pulkit Verma, P. Das
- Computer ScienceInternational Journal of Speech Technology
- 1 December 2015
This survey presents a comprehensive collection of research work related to i-vectors since its inception and discusses some recent trends of using i-VEctors in combination with other approaches.
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks
- Yizhong Wang, Swaroop Mishra, Daniel Khashabi
- Medicine
- 16 April 2022
These data support the concept that proper ED evaluation can identify a large body of patients with trivial ingestions who may not require hospital observation and help generalize NLP models to a variety of unseen tasks.
Learning Causal Models of Autonomous Agents using Interventions
- Pulkit Verma, Siddharth Srivastava
- Computer ScienceArXiv
- 21 August 2021
This work extends the analysis of an agent assessment module that lets an AI system execute high-level instruction sequences in simulators and answer the user queries about its execution of sequences of actions to efficiently derive a user-interpretable causal model of the system.
Asking the Right Questions: Learning Interpretable Action Models Through Query Answering
- Pulkit Verma, Shashank Rao Marpally, Siddharth Srivastava
- Computer ScienceAAAI Conference on Artificial Intelligence
- 18 May 2021
A new paradigm for estimating an interpretable, relational model of a black-box autonomous agent that can plan and act is developed using a rudimentary query interface with the agent and a hierarchical querying algorithm that generates an interrogation policy for estimating the agent's internal model in a user-interpretable vocabulary.
Improving services using mobile agents-based IoT in a smart city
- Pulkit Verma, Mayank Gupta, Tuhin Bhattacharya, P. Das
- Computer ScienceInternational Conferences on Contemporary…
- 1 November 2014
This paper presents a concept of an intelligent distributed layer using mobile agents which makes the system flexible and dynamically adaptable and can be used to deploy systems which can enable people to search for services using a common interface including voice commands.
A comparative study of resource usage for speaker recognition techniques
- Pulkit Verma, P. Das
- Computer ScienceInternational Computer Science Conference
- 1 December 2016
It is found that though i-vector approach requires more storage space, it is superior to the other two approaches in terms of memory and power consumption, which are critical factors for evaluating software performance in resource constrained mobile devices.
i-Vectors in speech processing applications: a survey
- Pulkit Verma, P. Das
- Computer ScienceInternational Journal of Speech Technology
- 6 August 2015
This survey presents a comprehensive collection of research work related to i-vectors since its inception and discusses some recent trends of using i-VEctors in combination with other approaches.
Differential Assessment of Black-Box AI Agents
- Rashmeet Kaur Nayyar, Pulkit Verma, Siddharth Srivastava
- Computer ScienceAAAI Conference on Artificial Intelligence
- 24 March 2022
This work proposes a novel approach to differentially assess black-box AI agents that have drifted from their previously known models and generates an active querying policy that selectively queries the agent and computes an updated model of its functionality.
Discovering User-Interpretable Capabilities of Black-Box Planning Agents
- Pulkit Verma, Shashank Rao Marpally, Siddharth Srivastava
- Computer ScienceInternational Conference on Principles of…
- 28 July 2021
This paper presents an algorithm for discovering from scratch the suite of high-level "capabilities" that an AI system with arbitrary internal planning algorithms/policies can perform and computes conditions describing the applicability and effects of these capabilities in user-interpretable terms.
...
...