arXiv subjects

Nelu Radpour

Publications and source records attributed to Nelu Radpour.

3 recordsLinked to original sources

arXiv2017

Conditional Generative Adversarial Networks for Emoji Synthesis with Word Embedding Manipulation

Emojis have become a very popular part of daily digital communication. Their appeal comes largely in part due to their ability to capture and elicit emotions in a more subtle and nuanced way than just plain text is able to. In line with recent advances in the field of deep learning, there are far reaching implications and applications that generative adversarial networks (GANs) can have for image generation. In this paper, we present a novel application of deep convolutional GANs (DC-GANs) with an optimized training procedure. We show that via incorporation of word embeddings conditioned on Google's word2vec model into the network, the generator is able to synthesize highly realistic emojis that are virtually identical to the real ones.

cs.CV↗

arXiv2017

Non-Contextual Modeling of Sarcasm using a Neural Network Benchmark

One of the most crucial components of natural human-robot interaction is artificial intuition and its influence on dialog systems. The intuitive capability that humans have is undeniably extraordinary, and so remains one of the greatest challenges for natural communicative dialogue between humans and robots. In this paper, we introduce a novel probabilistic modeling framework of identifying, classifying and learning features of sarcastic text via training a neural network with human-informed sarcastic benchmarks. This is necessary for establishing a comprehensive sentiment analysis schema that is sensitive to the nuances of sarcasm-ridden text by being trained on linguistic cues. We show that our model provides a good fit for this type of real-world informed data, with potential to achieve as accurate, if not more, than alternatives. Though the implementation and benchmarking is an extensive task, it can be extended via the same method that we present to capture different forms of nuances in communication and making for much more natural and engaging dialogue systems.

cs.CL↗

arXiv2017

Using Deep Convolutional Networks for Gesture Recognition in American Sign Language

In the realm of multimodal communication, sign language is, and continues to be, one of the most understudied areas. In line with recent advances in the field of deep learning, there are far reaching implications and applications that neural networks can have for sign language interpretation. In this paper, we present a method for using deep convolutional networks to classify images of both the the letters and digits in American Sign Language.

cs.CV↗