International Institute of Information Technology, Hyderabad

About: International Institute of Information Technology, Hyderabad is a education organization based out in Hyderabad, India. It is known for research contribution in the topics: Authentication & Internet security. The organization has 2048 authors who have published 3677 publications receiving 45319 citations. The organization is also known as: IIIT Hyderabad & International Institute of Information Technology (IIIT).

Deep Learning Techniques for Humor Detection in Hindi-English Code-Mixed Tweets

Abstract: We propose bilingual word embeddings based on word2vec and fastText models (CBOW and Skip-gram) to address the problem of Humor detection in Hindi-English code-mixed tweets in combination with deep learning architectures. We focus on deep learning approaches which are not widely used on code-mixed data and analyzed their performance by experimenting with three different neural network models. We propose convolution neural network (CNN) and bidirectional long-short term memory (biLSTM) (with and without Attention) models which take the generated bilingual embeddings as input. We make use of Twitter data to create bilingual word embeddings. All our proposed architectures outperform the state-of-the-art results, and Attention-based bidirectional LSTM model achieved an accuracy of 73.6% which is an increment of more than 4% compared to the current state-of-the-art results.

A Novel Approach Towards Incorporating Context Processing Capabilities in NLIDB System

Abstract: This paper presents a novel approach to categorize, model and identify contextual information in natural language interface to database (NLIDB) systems. The interactions between user and system are categorized and modeled based on the way in which the contextual information is utilized in the interactions. A relationship schema among the responses (user and system responses) is proposed. We present a novel method to identify contextual information in one specific type of usersystem interaction. We report on results of experiments with the university related queries.

Urea Mimics Nucleobases by Preserving the Helical Integrity of B-DNA Duplexes via Hydrogen Bonding and Stacking Interactions.

Abstract: Urea lesions are formed in DNA because of free radical damage of the thymine base, and their occurrence in DNA blocks DNA polymerases, which has deleterious consequences. Recently, it has been shown that urea is capable of forming hydrogen bonding and stacking interactions with nucleobases, which are responsible for the unfolding of RNA in aqueous urea. Base pairing and stacking are inherent properties of nucleobases; because urea is able to form both, this study attempts to investigate if urea can mimic nucleobases in the context of nucleic acid structures by examining the effect of introducing urea lesions complementary to the four different nucleobases on the overall helical integrity of B-DNA duplexes and their thermodynamic stabilities using molecular dynamics (MD) simulations. The MD simulations resulted in stable duplexes without significant changes in the global B-DNA conformation. The urea lesions occupy intrahelical positions by forming hydrogen bonds with nitrogenous nucleobases, in agreement w...

FNNC: Achieving Fairness through Neural Networks

Abstract: In classification models fairness can be ensured by solving a constrained optimization problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and Equalized Odds, which are non-decomposable and non-convex. Researchers define convex surrogates of the constraints and then apply convex optimization frameworks to obtain fair classifiers. Surrogates serve only as an upper bound to the actual constraints, and convexifying fairness constraints might be challenging. We propose a neural network-based framework, \emph{FNNC}, to achieve fairness while maintaining high accuracy in classification. The above fairness constraints are included in the loss using Lagrangian multipliers. We prove bounds on generalization errors for the constrained losses which asymptotically go to zero. The network is optimized using two-step mini-batch stochastic gradient descent. Our experiments show that FNNC performs as good as the state of the art, if not better. The experimental evidence supplements our theoretical guarantees. In summary, we have an automated solution to achieve fairness in classification, which is easily extendable to many fairness constraints.

Towards adaptive autopilots for fixed-wing unmanned aerial vehicles

Abstract: Control of fixed-wing Unmanned Aerial Vehicles (UAVs) is typically organized according to two layers: the low-level control or autopilot, and the high-level control or guidance. The disadvantage of this modular design is that an intelligent guidance layer may become ineffective if the autopilot layer cannot deal with uncertainty. In fact, the required knowledge derived from linearization of equations of motion (trimming points) makes most autopilots sensitive to uncertainty. In this work, we study an autopilot framework where the knowledge of the UAV dynamics and of trimming points is not required. The proposed design, tested with complex UAV dynamics, can emulate the behavior of a carefully tuned off-the-shelf autopilot, without using its a priori knowledge.