Algorithms based on deep neural networks (DNNs) have attracted increasing attention from the scientific computing community.
Computational Physics Analysis of PDEs
The proposed MRFGAT architecture is tested on ModelNet10 and ModelNet40 datasets, and results show it achieves state-of-the-art performance in shape classification tasks.
As an extension of this framework, we propose a novel method to train one shared Transformer network for multilingual machine translation with different layer selection posteriors for each language pair.
Recent work demonstrates the potential of multilingual pretraining of creating one model that can be used for various tasks in different languages.
This paper proposes a simple and effective approach to address the problem of posterior collapse in conditional variational autoencoders (CVAEs).
We describe the finding of the Fourth Workshop on Neural Generation and Translation, held in concert with the annual conference of the Association for Computational Linguistics (ACL 2020).
no code implementations • 24 Jun 2020 • Xin Luna Dong, Xiang He, Andrey Kan, Xi-An Li, Yan Liang, Jun Ma, Yifan Ethan Xu, Chenwei Zhang, Tong Zhao, Gabriel Blanco Saldana, Saurabh Deshpande, Alexandre Michetti Manduca, Jay Ren, Surender Pal Singh, Fan Xiao, Haw-Shiuan Chang, Giannis Karamanolakis, Yuning Mao, Yaqing Wang, Christos Faloutsos, Andrew McCallum, Jiawei Han
Can one build a knowledge graph (KG) for all products in the world?
(1) We formalize the problem of validating the textual attribute values of products from a variety of categories as a natural language inference task in the few-shot learning setting, and propose a meta-learning latent variable model to jointly process the signals obtained from product profiles and textual attribute values.
For BART we get the best performance by freezing most of the model parameters, and adding extra positional embeddings.
This paper demonstrates that multilingual denoising pre-training produces significant performance gains across a wide variety of machine translation (MT) tasks.
Posterior collapse plagues VAEs for text, especially for conditional text generation with strong autoregressive decoders.
Most sequence-to-sequence (seq2seq) models are autoregressive; they generate each token by conditioning on previously generated tokens.
Ranked #3 on Machine Translation on WMT2016 English-Romanian
To address the problem, this paper proposes an efficient sampling and evaluation framework, which aims to provide quality accuracy evaluation with strong statistical guarantee while minimizing human efforts.
We share the findings of the first shared task on improving robustness of Machine Translation (MT).
Adversarial examples have been shown to be an effective way of assessing the robustness of neural sequence-to-sequence (seq2seq) models, by applying perturbations to the input of a model leading to large degradation in performance.
Adversarial examples --- perturbations to the input of a model that elicit large changes in the output --- have been shown to be an effective way of assessing the robustness of sequence-to-sequence (seq2seq) models.
In addition, we have observed that the class prior distributions differ significantly between the languages.
3 code implementations • • Sercan O. Arik, Mike Chrzanowski, Adam Coates, Gregory Diamos, Andrew Gibiansky, Yongguo Kang, Xi-An Li, John Miller, Andrew Ng, Jonathan Raiman, Shubho Sengupta, Mohammad Shoeybi
We present Deep Voice, a production-quality text-to-speech system constructed entirely from deep neural networks.