Filters








10 Hits in 6.1 sec

Deep Learning for Text Style Transfer: A Survey [article]

Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, Rada Mihalcea
2021 arXiv   pre-print
We also provide discussions on a variety of important topics regarding the future development of this task. Our curated paper list is at https://github.com/zhijing-jin/Text_Style_Transfer_Survey  ...  In this paper, we present a systematic survey of the research on neural text style transfer, spanning over 100 representative articles since the first neural text style transfer work in 2017.  ...  17-21, 2015, pages 379–389, The Beijing, China, 21-26 June 2014, volume 32 of Association for Computational Linguistics.  ... 
arXiv:2011.00416v5 fatcat:wfw3jfh2mjfupbzrmnztsqy4ny

Deep Learning for Text Style Transfer: A Survey

Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, Rada Mihalcea
2021 Computational Linguistics  
We also provide discussions on a variety of important topics regarding the future development of this task.  ...  In this paper, we present a systematic survey of the research on neural text style transfer, spanning over 100 representative articles since the first neural text style transfer work in 2017.  ...  September 17-21, 2015, pages 379–389, The Beijing, China, 21-26 June 2014, volume 32 of Association for Computational Linguistics.  ... 
doi:10.1162/coli_a_00426 fatcat:v7vmb62ckfcu5k5mpu2pydnrxy

Deep Generative Model for Joint Alignment and Word Representation [article]

Miguel Rios and Wilker Aziz and Khalil Sima'an
2018 arXiv   pre-print
This work exploits translation data as a source of semantically relevant learning signal for models of word representation.  ...  We investigate our model's performance on a range of lexical semantics tasks achieving competitive results on several standard benchmarks including natural language inference, paraphrasing, and text similarity  ...  ing, ICML 2014, Beijing, China, 21-26 June arXiv preprint arXiv:1412.6623 . 2014. pages 1278–1286.  ... 
arXiv:1802.05883v3 fatcat:quez2zxjqzf2nbfbvaunchcs34

Scalable Discrete Sampling as a Multi-Armed Bandit Problem [article]

Yutian Chen, Zoubin Ghahramani
2016 arXiv   pre-print
Drawing a sample from a discrete distribution is one of the building components for Monte Carlo methods.  ...  Empirical evaluations show the robustness and efficiency of the approximate algorithms in both synthetic and real-world large-scale problems.  ...  Acknowledgements We thank Matt Hoffman for helpful discussions on the connection of our work to the MAB problems. We also thank all the reviewers for their constructive comments.  ... 
arXiv:1506.09039v3 fatcat:l6zuqsnzdrf7dguz7btqsldylm

Worst Cases Policy Gradients [article]

Yichuan Charlie Tang, Jian Zhang, Ruslan Salakhutdinov
2019 arXiv   pre-print
The learned policy can map the same state to different actions depending on the propensity for risk.  ...  Towards this goal, we propose an actor-critic framework that models the uncertainty of the future and simultaneously learns a policy based on that uncertainty model.  ...  In Proceedings of the 31th International Conference on Machine Learning, ICML 2014, Beijing, China, 21-26 June 2014, pages 387–395, 2014.  ... 
arXiv:1911.03618v1 fatcat:allc4pk3qzburak6jg6rcmnqdy

Invertible generative models for inverse problems: mitigating representation error and dataset bias [article]

Muhammad Asim, Max Daniels, Oscar Leong, Ali Ahmed, Paul Hand
2020 arXiv   pre-print
We additionally compare performance for compressive sensing to unlearned methods, such as the deep decoder, and we establish theoretical bounds on expected recovery error in the case of a linear invertible  ...  better reconstructions than GAN priors for images that have rare features of variation within the biased training set, including out-of-distribution natural images.  ...  In Proceedings of the 31th International Conference on Machine Learning, ICML 2014, Beijing, China, 21-26 June 2014, volume 32 of JMLR Workshop and Conference Proceedings, pp. 1278-1286.  ... 
arXiv:1905.11672v4 fatcat:hgpfoh6frfa4thyxvhmqjzqomi

Winning the NIST Contest: A scalable and general approach to differentially private synthetic data

Ryan McKenna, Gerome Miklau, Daniel Sheldon
2021 Journal of Privacy and Confidentiality  
NIST-MST was the winning mechanism in the 2018 NIST differential privacy synthetic data competition, and MST is a new mechanism that can work in more general settings, while still performing comparably  ...  a noise addition mechanism, and (3) generate synthetic data that preserves the measured marginals well.  ...  In Proceedings of the 31th International Conference on Machine Learning, ICML 2014, Beijing, China, 21-26 June 2014, volume 32 of JMLR Workshop and Conference Proceedings.  ... 
doi:10.29012/jpc.778 fatcat:b2s37gulojbxxm2buyrfzw7vq4

Low-Precision Random Fourier Features for Memory-Constrained Kernel Approximation [article]

Jian Zhang, Avner May, Tri Dao, Christopher Ré
2019 arXiv   pre-print
Building on recent theoretical work, we define a measure of kernel approximation error which we find to be more predictive of the empirical generalization performance of kernel approximation methods than  ...  Empirically, we demonstrate across four benchmark datasets that LP-RFFs can match the performance of full-precision RFFs and the Nyström method, with 3x-10x and 50x-460x less memory, respectively.  ...  Acknowledgements We thank Michael Collins for his helpful guidance on the Nyström vs. RFF experiments in Avner May's PhD dissertation (May, 2018), which inspired this work.  ... 
arXiv:1811.00155v2 fatcat:6bfj2vqiobhm7ltfizjtxu575q

Exploration--Exploitation in MDPs with Options [article]

Ronan Fruit, Alessandro Lazaric
2017 arXiv   pre-print
In this paper, we derive an upper and lower bound on the regret of a variant of UCRL using options.  ...  simple scenarios in which the regret of learning with options can be provably much smaller than the regret suffered when learning with primitive actions.  ...  In Proceedings of the 31th International Conference on Machine Learning, ICML 2014, Beijing, China, 21-26 June 2014, pages 1350-1358, 2014. Amy McGovern and Andrew G. Barto.  ... 
arXiv:1703.08667v2 fatcat:dsqwd2rd4je73cc5mbk3b2qb2u

Global Riemannian Acceleration in Hyperbolic and Spherical Spaces [article]

David Martínez-Rubio
2022 arXiv   pre-print
) or μ-strongly g-convex functions defined on the hyperbolic space or a subset of the sphere.  ...  We further research on the accelerated optimization phenomenon on Riemannian manifolds by introducing accelerated global first-order methods for the optimization of L-smooth and geodesically convex (g-convex  ...  Acknowledgments We thank Mario Lezcano-Casado for helpful discussions on this work. We thank Varun Kanade and Patrick Rebeschini for proofreading of this work.  ... 
arXiv:2012.03618v4 fatcat:dymhmosw6nh4finmhfnzzraxuu