International Institute of Information Technology

About: International Institute of Information Technology is a education organization based out in Pune, India. It is known for research contribution in the topics: Wireless sensor network & Authentication. The organization has 1205 authors who have published 1405 publications receiving 12619 citations.

Deep Learning for Hate Speech Detection in Tweets

Abstract: Hate speech detection on Twitter is critical for applications like controversial event extraction, building AI chatterbots, content recommendation, and sentiment analysis. We define this task as being able to classify a tweet as racist, sexist or neither. The complexity of the natural language constructs makes this task very challenging. We perform extensive experiments with multiple deep learning architectures to learn semantic word embeddings to handle this complexity. Our experiments on a benchmark dataset of 16K annotated tweets show that such deep learning methods outperform state-of-the-art char/word n-gram methods by ~18 F1 points.

Deep Learning for Hate Speech Detection in Tweets

Abstract: Hate speech detection on Twitter is critical for applications like controversial event extraction, building AI chatterbots, content recommendation, and sentiment analysis. We define this task as being able to classify a tweet as racist, sexist or neither. The complexity of the natural language constructs makes this task very challenging. We perform extensive experiments with multiple deep learning architectures to learn semantic word embeddings to handle this complexity. Our experiments on a benchmark dataset of 16K annotated tweets show that such deep learning methods outperform state-of-the-art char/word n-gram methods by ~18 F1 points.

Unsupervised Learning from Narrated Instruction Videos

Abstract: We address the problem of automatically learning the main steps to complete a certain task, such as changing a car tire, from a set of narrated instruction videos. The contributions of this paper are three-fold. First, we develop a new unsupervised learning approach that takes advantage of the complementary nature of the input video and the associated narration. The method solves two clustering problems, one in text and one in video, applied one after each other and linked by joint constraints to obtain a single coherent sequence of steps in both modalities. Second, we collect and annotate a new challenging dataset of real-world instruction videos from the Internet. The dataset contains about 800,000 frames for five different tasks1 that include complex interactions between people and objects, and are captured in a variety of indoor and outdoor settings. Third, we experimentally demonstrate that the proposed method can automatically discover, in an unsupervised manner, the main steps to achieve the task and locate the steps in the input videos.

Soft Actuators for Soft Robotic Applications: A Review

Abstract: The authors acknowledge generous support of the King Abdullah University of Science and Technology (KAUST). The authors acknowledge Dr. Joanna M. Nassar, Dr. Galo A. Torres, Dr. Mohamed T. Ghoneim, Andres A. Aguirre-Pablo, Davide Priante, Dr. Jhonathan P. Rojas, Sigurdur T. Thoroddsen, and Prof. Boon S. Ooi who contributed to the “pause-embed-resume” data. The authors thank Kelly Rader for proof reading this manuscript.

Telecommunications Infrastructure and Economic Growth: Evidence from Developing Countries

Abstract: In this study, we investigate empirically the relationship between telephone penetration and economic growth, using data for developing countries. Using 3SLS, we estimate a system of equations that endogenizes economic growth and telecom penetration. We find that the traditional economic factors explain demand for mainline and mobile phones, even in developing countries. We find positive impacts of mobile and landline phones on national output, when we control for the effects of capital and labor. We discuss the associated policy implications related to improvement of telecom penetration in developing countries.