Search Results for author: Sayan Ghosh

Found 22 papers, 5 papers with code

Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learning

no code implementations2 Oct 2021 Sayan Ghosh, Shashank Srivastava

On the VirtualHome framework, we get improvements of up to 9. 0% on the Longest Common Subsequence metric and 14. 7% on recall-based metrics over previous work on this framework (Puig et al., 2018).

Opacus: User-Friendly Differential Privacy Library in PyTorch

no code implementations25 Sep 2021 Ashkan Yousefpour, Igor Shilov, Alexandre Sablayrolles, Davide Testuggine, Karthik Prasad, Mani Malek, John Nguyen, Sayan Ghosh, Akash Bharadwaj, Jessica Zhao, Graham Cormode, Ilya Mironov

We introduce Opacus, a free, open-source PyTorch library for training deep learning models with differential privacy (hosted at opacus. ai).

Adversarial Scrubbing of Demographic Information for Text Classification

1 code implementation17 Sep 2021 Somnath Basu Roy Chowdhury, Sayan Ghosh, Yiyuan Li, Junier B. Oliva, Shashank Srivastava, Snigdha Chaturvedi

Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated target task.

Classification Text Classification

ePiC: Employing Proverbs in Context as a Benchmark for Abstract Language Understanding

no code implementations14 Sep 2021 Sayan Ghosh, Shashank Srivastava

While large language models have shown exciting progress on several NLP benchmarks, evaluating their ability for complex analogical reasoning remains under-explored.

Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media

no code implementations14 Apr 2021 Sayan Ghosh, Dylan Baker, David Jurgens, Vinodkumar Prabhakaran

Online social media platforms increasingly rely on Natural Language Processing (NLP) techniques to detect abusive content at scale in order to mitigate the harms it causes to their users.

Bias Detection

Importance-based Multimodal Autoencoder

no code implementations1 Jan 2021 Sayan Ghosh, Eugene Laksana, Louis-Philippe Morency, Stefan Scherer

In this paper we propose the IMA (Importance-based Multimodal Autoencoder) model, a scalable model that learns modality importances and robust multimodal representations through a novel cross-covariance based loss function.

Data-based Discovery of Governing Equations

no code implementations5 Dec 2020 Waad Subber, Piyush Pandita, Sayan Ghosh, Genghis Khan, Liping Wang, Roger Ghanem

Without a prior definition of the model structure, first a free-form of the equation is discovered, and then calibrated and validated against the available data.

PRover: Proof Generation for Interpretable Reasoning over Rules

2 code implementations EMNLP 2020 Swarnadeep Saha, Sayan Ghosh, Shashank Srivastava, Mohit Bansal

First, PROVER generates proofs with an accuracy of 87%, while retaining or improving performance on the QA task, compared to RuleTakers (up to 6% improvement on zero-shot evaluation).

Data-Informed Decomposition for Localized Uncertainty Quantification of Dynamical Systems

no code implementations14 Aug 2020 Waad Subber, Sayan Ghosh, Piyush Pandita, Yiming Zhang, Liping Wang

The region of interest can be specified based on the localization features of the solution, user interest, and correlation length of the random material properties.

Bayesian Inference

A Fully Bayesian Gradient-Free Supervised Dimension Reduction Method using Gaussian Processes

2 code implementations8 Aug 2020 Raphael Gautier, Piyush Pandita, Sayan Ghosh, Dimitri Mavris

The comparison shows that the proposed method improves the active subspace recovery and predictive accuracy, in both the deterministic and probabilistic sense, when only few model observations are available for training, at the cost of increased training time.

Dimensionality Reduction Gaussian Processes

Analysing the Extent of Misinformation in Cancer Related Tweets

no code implementations30 Mar 2020 Rakesh Bal, Sayan Sinha, Swastika Dutta, Rishabh Joshi, Sayan Ghosh, Ritam Dutt

This helps spread awareness regarding the various causes, cures and prevention methods of cancer.

Misinformation

Advances in Bayesian Probabilistic Modeling for Industrial Applications

no code implementations26 Mar 2020 Sayan Ghosh, Piyush Pandita, Steven Atkinson, Waad Subber, Yiming Zhang, Natarajan Chennimalai Kumar, Suryarghya Chakrabarti, Liping Wang

The methodology, called GE's Bayesian Hybrid Modeling (GEBHM), is a probabilistic modeling method, based on the Kennedy and O'Hagan framework, that has been continuously scaled-up and industrialized over several years.

Bayesian task embedding for few-shot Bayesian optimization

1 code implementation2 Jan 2020 Steven Atkinson, Sayan Ghosh, Natarajan Chennimalai-Kumar, Genghis Khan, Liping Wang

We describe a method for Bayesian optimization by which one may incorporate data from multiple systems whose quantitative interrelationships are unknown a priori.

Bayesian Inference

A Strategy for Adaptive Sampling of Multi-fidelity Gaussian Process to Reduce Predictive Uncertainty

no code implementations26 Jul 2019 Sayan Ghosh, Jesper Kristensen, Yiming Zhang, Waad Subber, Liping Wang

Multi-fidelity Gaussian process is a common approach to address the extensive computationally demanding algorithms such as optimization, calibration and uncertainty quantification.

DeepTagRec: A Content-cum-User based Tag Recommendation Framework for Stack Overflow

no code implementations10 Mar 2019 Suman Kalyan Maity, Abhishek Panigrahi, Sayan Ghosh, Arundhati Banerjee, Pawan Goyal, Animesh Mukherjee

In this paper, we develop a content-cum-user based deep learning framework DeepTagRec to recommend appropriate question tags on Stack Overflow.

Public Sphere 2.0: Targeted Commenting in Online News Media

no code implementations21 Feb 2019 Ankan Mullick, Sayan Ghosh, Ritam Dutt, Avijit Ghosh, Abhijnan Chakraborty

Because the readers lack the time to go over an entire article, most of the comments are relevant to only particular sections of an article.

Learning Representations of Affect from Speech

no code implementations15 Nov 2015 Sayan Ghosh, Eugene Laksana, Louis-Philippe Morency, Stefan Scherer

Experiments on a well-established real-life speech dataset (IEMOCAP) show that the learnt representations are comparable to state of the art feature extractors (such as voice quality features and MFCCs) and are competitive with state-of-the-art approaches at emotion and dimensional affect recognition.

Denoising Emotion Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.