AIFounded | Research
AI Powered Knowledge Engine - Building Smarter Apps - Harness the power of a smarter AI educated with the entire world's data and facts.
ai founded, founded, ai, machine learning, deep learning, bigdata, big data, data, machine, learning, artificial, intelligence, artificial intelligence, deep, learning, technology, tech, toronto, startup, agent, smart, data science, science, data enrichment, data analytics, analytics, search, search engine, information technology, autonomous, nlp, natural language processing, language processing, processing, computational linguistics, linguistics, natural language, data capture, development, image recognition, research, research and development, enterprise intelligence, ethics, ai ethics, ai security, data search, aggregation, information retrieval, information, data extraction, data retrieval, extraction, text synthesis
209
page-template,page-template-full_width,page-template-full_width-php,page,page-id-209,ajax_fade,page_not_loaded,,qode-title-hidden,qode_grid_1300,qode-theme-ver-10.1.1,wpb-js-composer js-comp-ver-5.0.1,vc_responsive

Neural Machine Translation with Gumbel-Greedy Decoding

 

Previous neural machine translation models used some heuristic search algorithms (e.g., beam search) in order to avoid solving the maximum a posteriori problem over translation sentences at test time. In this paper, we propose the Gumbel-Greedy Decoding which trains a generative network to predict translation under a trained model. We solve such a problem using the Gumbel-Softmax reparameterization, which makes our generative network differentiable and trainable through standard stochastic gradient methods. We empirically demonstrate that our proposed model is effective for generating sequences of discrete words.

 

ARXIV

COLLABORATORS

Generative Advesarial Parallelization

 

Generative Adversarial Networks (GAN) have become one of the most studied frameworks for unsupervised learning due to their intuitive formulation. They have also been shown to be capable of generating convincing examples in limited domains, such as low-resolution images. However, they still prove difficult to train in practice and tend to ignore modes of the data generating distribution. Quantitatively capturing effects such as mode coverage and more generally the quality of the generative model still remain elusive. We propose Generative Adversarial Parallelization (GAP), a framework in which many GANs or their variants are trained simultaneously, exchanging their discriminators. This eliminates the tight coupling between a generator and discriminator, leading to improved convergence and improved coverage of modes. We also propose an improved variant of the recently proposed Generative Adversarial Metric and show how it can score individual GANs or their collections under the GAP model.

 

ARXIV

COLLABORATORS

UGlogo-justblackbox