Related papers: Speaking the Same Language: Matching Machine to Hu…
This work presents a thorough review concerning recent studies and text generation advancements using Generative Adversarial Networks. The usage of adversarial learning for text generation is promising as it provides alternatives to…
Research on generative models to produce human-aligned / human-preferred outputs has seen significant recent contributions. Between text and image-generative models, we narrowed our focus to text-based generative models, particularly to…
Automatic evaluation of language generation systems is a well-studied problem in Natural Language Processing. While novel metrics are proposed every year, a few popular metrics remain as the de facto metrics to evaluate tasks such as image…
Adversarial training is a common approach for bias mitigation in natural language processing. Although most work on debiasing is motivated by equal opportunity, it is not explicitly captured in standard adversarial training. In this paper,…
Automatically generating natural language descriptions from an image is a challenging problem in artificial intelligence that requires a good understanding of the visual and textual signals and the correlations between them. The…
The Visual Dialogue task requires an agent to engage in a conversation about an image with a human. It represents an extension of the Visual Question Answering task in that the agent needs to answer a question about an image, but it needs…
Modern applications and progress in deep learning research have created renewed interest for generative models of text and of images. However, even today it is unclear what objective functions one should use to train and evaluate these…
Robots will eventually be part of every household. It is thus critical to enable algorithms to learn from and be guided by non-expert users. In this paper, we bring a human in the loop, and enable a human teacher to give feedback to a…
We propose to generate adversarial samples by modifying activations of upper layers encoding semantically meaningful concepts. The original sample is shifted towards a target sample, yielding an adversarial sample, by using the modified…
As advanced modern systems like deep neural networks (DNNs) and generative AI continue to enhance their capabilities in producing convincing and realistic content, the need to distinguish between user-generated and machine generated content…
The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to…
Adversarial samples are strategically modified samples, which are crafted with the purpose of fooling a classifier at hand. An attacker introduces specially crafted adversarial samples to a deployed classifier, which are being…
Image captioning, which generates natural language descriptions of the visual information in an image, is a crucial task in vision-language research. Previous models have typically addressed this task by aligning the generative capabilities…
We compare the 0-shot performance of a neural caption-based image retriever when given as input either human-produced captions or captions generated by a neural captioner. We conduct this comparison on the recently introduced ImageCoDe…
Despite the dramatic success in image generation, Generative Adversarial Networks (GANs) still face great challenges in synthesizing sequences of discrete elements, in particular human language. The difficulty in generator training arises…
Constructing an organized dataset comprised of a large number of images and several captions for each image is a laborious task, which requires vast human effort. On the other hand, collecting a large number of images and sentences…
Automatic generation of natural language from images has attracted extensive attention. In this paper, we take one step further to investigate generation of poetic language (with multiple lines) to an image for automatic poetry creation.…
Generative Adversarial Networks (GANs) have been promising in the field of image generation, however, they have been hard to train for language generation. GANs were originally designed to output differentiable values, so discrete language…
Text-based image captioning (TextCap) requires simultaneous comprehension of visual content and reading the text of images to generate a natural language description. Although a task can teach machines to understand the complex human…
Many natural language related applications involve text generation, created by humans or machines. While in many of those applications machines support humans, yet in few others, (e.g. adversarial machine learning, social bots and trolls)…