Gursimran Singh
Gursimran Singh has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
M. Vijaya Raju
Dept. of CSE/IT, Lovely Prof. Univ., Phagwara, India
1 shared publication- Shashank Srikant
Computer Science & Artificial Intelligence Laboratory, Massachusetts Institute of Technology
1 shared publication - Varun Aggarwal
Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA
1 shared publication
Latest Publications
- Open Access
- 13 August 2016
- Published by Association for Computing Machinery (ACM)
- p. 263-272
Question Independent Grading using Machine Learning
Learning supervised models to grade open-ended responses is an expensive process. A model has to be trained for every prompt/question separately, which in turn requires graded samples. In automatic programming evaluation specifically, the focus of this work, this issue is amplified. The models have to be trained not only for every question but also for every language the question is offered in. Moreover, the availability and time taken by experts to create a labeled set of programs for each question is a major bottleneck in scaling such a system. We address this issue by presenting a method to grade computer programs which requires no manually assigned labeled samples for grading responses to a new, unseen question. We extend our previous work [25] wherein we introduced a grammar of features to learn question specific models. In this work, we propose a method to transform those features into a set of features that maintain their structural relation with the labels across questions. Using these features we learn one supervised model, across questions for a given language, which can then be applied to an ungraded response to an unseen question. We show that our method rivals the performance of both, question specific models and the consensus among human experts while substantially outperforming extant ways of evaluating codes. We demonstrate the system single s value by deploying it to grade programs in a high stakes assessment. The learning from this work is transferable to other grading tasks such as math question grading and also provides a new variation to the supervised learning approach.
- 13 August 2016
- Published by Association for Computing Machinery (ACM)
- p. 263-272
Open AccessQuestion Independent Grading using Machine Learning
Learning supervised models to grade open-ended responses is an expensive process. A model has to be trained for every prompt/question separately, which in turn requires graded samples. In automatic programming evaluation specifically, the focus of this work, this issue is amplified. The models have to be trained not only for every question but also for every language the question is offered in. Moreover, the availability and time taken by experts to create a labeled set of programs for each question is a major bottleneck in scaling such a system. We address this issue by presenting a method to grade computer programs which requires no manually assigned labeled samples for grading responses to a new, unseen question. We extend our previous work [25] wherein we introduced a grammar of features to learn question specific models. In this work, we propose a method to transform those features into a set of features that maintain their structural relation with the labels across questions. Using these features we learn one supervised model, across questions for a given language, which can then be applied to an ungraded response to an unseen question. We show that our method rivals the performance of both, question specific models and the consensus among human experts while substantially outperforming extant ways of evaluating codes. We demonstrate the system single s value by deploying it to grade programs in a high stakes assessment. The learning from this work is transferable to other grading tasks such as math question grading and also provides a new variation to the supervised learning approach.
- 1 September 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 350-355
Dual Gateway Routing Protocol
Dependency on Computer Networks is growing Day by Day. Many new services have been introduced which leads the popularity of the internet to next level, for example VoIP (Voice over Internet), E-Banking, Telepresence etc. Uninterrupted service is the most important requirement of the computer networks, the main reason behind this requirement is dependency on computer networks. Uninterrupted service or high availability can be achieved through redundancy and Redundancy Protocols, Redundancy can be achieved easily but efficient use of available resources is somewhat difficult task. So in this paper we will discuss a new redundancy mechanism which tries to use available resources efficiently, and make networks more fault tolerant.
- 1 September 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 350-355
Dual Gateway Routing Protocol
Dependency on Computer Networks is growing Day by Day. Many new services have been introduced which leads the popularity of the internet to next level, for example VoIP (Voice over Internet), E-Banking, Telepresence etc. Uninterrupted service is the most important requirement of the computer networks, the main reason behind this requirement is dependency on computer networks. Uninterrupted service or high availability can be achieved through redundancy and Redundancy Protocols, Redundancy can be achieved easily but efficient use of available resources is somewhat difficult task. So in this paper we will discuss a new redundancy mechanism which tries to use available resources efficiently, and make networks more fault tolerant.