1 code implementation • CoNLL (EMNLP) 2021 • Shikhar Bharadwaj, Shirish Shevade
Natural language processing for program synthesis has been widely researched.
1 code implementation • NAACL 2022 • Shikhar Bharadwaj, Shirish Shevade
We observe a 1. 8x improvement in the inference time and a 5x reduction in model parameters.
1 code implementation • 17 Sep 2022 • Surya Prakash Sahu, Madhurima Mandal, Shikhar Bharadwaj, Aditya Kanade, Petros Maniatis, Shirish Shevade
Compared to the existing datasets, in CodeQueries, the queries are about code semantics, the context is file level and the answers are code spans.
2 code implementations • 4 Oct 2021 • Vijaikumar M, Deepesh Hada, Shirish Shevade
The personalized list continuation (PLC) task is to curate the next items to user-generated lists (ordered sequence of items) in a personalized way.
1 code implementation • 12 Jul 2021 • Soham Pal, Yash Gupta, Aditya Kanade, Shirish Shevade
Machine-Learning-as-a-Service providers expose machine learning (ML) models through application programming interfaces (APIs) to developers.
1 code implementation • 7 Feb 2020 • Soham Pal, Yash Gupta, Aditya Shukla, Aditya Kanade, Shirish Shevade, Vinod Ganapathy
We demonstrate that (1) it is possible to use ACTIVETHIEF to extract deep classifiers trained on a variety of datasets from image and text domains, while querying the model with as few as 10-30% of samples from public datasets, (2) the resulting model exhibits a higher transferability success rate of adversarial examples than prior work, and (3) the attack evades detection by the state-of-the-art model extraction detection method, PRADA.
1 code implementation • NeurIPS 2019 • Rahul Gupta, Aditya Kanade, Shirish Shevade
In this work, we present NeuralBugLocator, a deep learning based technique, that can localize the bugs in a faulty program with respect to a failing test, without even running the program.
no code implementations • 19 Jul 2019 • Vijaikumar M, Shirish Shevade, M. N. Murty
Cross-Domain Collaborative Filtering (CDCF) provides a way to alleviate data sparsity and cold-start problems present in recommendation systems by exploiting the knowledge from related domains.
no code implementations • 28 May 2019 • Rahul Gupta, Aditya Kanade, Shirish Shevade
To localize the bugs, we analyze the trained network using a state-of-the-art neural prediction attribution technique and see which lines of the programs make it predict the test outcomes.
no code implementations • 22 May 2019 • Soham Pal, Yash Gupta, Aditya Shukla, Aditya Kanade, Shirish Shevade, Vinod Ganapathy
Machine learning models trained on confidential datasets are increasingly being deployed for profit.
no code implementations • 13 Apr 2018 • Ishan Rastogi, Aditya Kanade, Shirish Shevade
In this work, we propose an automated method to identify semantic bugs in student programs, called ATAS, which builds upon the recent advances in both symbolic execution and active learning.
1 code implementation • 31 Jan 2018 • Rahul Gupta, Aditya Kanade, Shirish Shevade
Novice programmers often struggle with the formal syntax of programming languages.
Ranked #4 on Program Repair on DeepFix
no code implementations • EMNLP 2017 • Deepak P, Dinesh Garg, Shirish Shevade
The idea is that such a space mirrors semantic similarity among questions as well as answers, thereby enabling high quality retrieval.
1 code implementation • 4 Feb 2017 • Rahul Gupta, Soham Pal, Aditya Kanade, Shirish Shevade
The problem of automatically fixing programming errors is a very active research topic in software engineering.
no code implementations • 1 Aug 2016 • Madhusudan Lakshmana, Sundararajan Sellamanickam, Shirish Shevade, Keerthi Selvaraj
Motivated by this observation, we propose to learn kernels with semantic coherence using clustering scheme combined with Word2Vec representation and domain knowledge such as SentiWordNet.
no code implementations • 4 Apr 2016 • Divya Padmanabhan, Satyanath Bhat, Shirish Shevade, Y. Narahari
Multi-label classification is a common supervised machine learning problem where each instance is associated with multiple classes.
no code implementations • 25 Jan 2016 • Divya Padmanabhan, Satyanath Bhat, Dinesh Garg, Shirish Shevade, Y. Narahari
We study the problem of training an accurate linear regression model by procuring labels from multiple noisy crowd annotators, under a budget constraint.
no code implementations • 25 Dec 2014 • P. K. Srijith, P. Balamurugan, Shirish Shevade
We provide Gaussian process models based on pseudo-likelihood approximation to perform sequence labeling.
no code implementations • 11 Nov 2013 • P. Balamurugan, Shirish Shevade, S. Sundararajan, S. S Keerthi
Here, we focus on discriminative models for sequence labeling.
no code implementations • 9 Nov 2013 • P. Balamurugan, Shirish Shevade, Sundararajan Sellamanickam
The optimization problem, which in general is not convex, contains the loss terms associated with the labelled and unlabelled examples along with the domain constraints.