A Content-Based Neural Reordering Model for Statistical Machine Translation

Pan, Yuanlong; Xiao, Li; Yang, Ya-Ting Carolyn; Mi, Chenggang; Dong, Rui; Zeng, Wei

doi:10.1007/978-981-10-7134-8_11

Cited by 7 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future, many directions seem attractive and inspiring. It is quite important to decompose the knowledge learned/transferred, which to some extent is like the decomposition of different features in deep learning for the interpretability of AGI and AI [1][2][3]21,22].…”

Section: Discussionmentioning

confidence: 99%

Decomposition Is All You Need: Single-Objective to Multi-Objective Optimization towards Artificial General Intelligence

Xu,

Wang,

Guo

et al. 2023

Mathematics

View full text Add to dashboard Cite

As a new abstract computational model in evolutionary transfer optimization (ETO), single-objective to multi-objective optimization (SMO) is conducted at the macroscopic level rather than the intermediate level for specific algorithms or the microscopic level for specific operators; this method aims to develop systems with a profound grasp of evolutionary dynamic and learning mechanism similar to human intelligence via a “decomposition” style (in the abstract of the well-known “Transformer” article “Attention is All You Need”, they use “attention” instead). To the best of our knowledge, it is the first work of SMO for discrete cases because we extend our conference paper and inherit its originality status. In this paper, by implementing the abstract SMO in specialized memetic algorithms, key knowledge from single-objective problems/tasks to the multi-objective core problem/task can be transferred or “gathered” for permutation flow shop scheduling problems, which will reduce the notorious complexity in combinatorial spaces for multi-objective settings in a straight method; this is because single-objective tasks are easier to complete than their multi-objective versions. Extensive experimental studies and theoretical results on benchmarks (1) emphasize our decomposition root in mathematical programming, such as Lagrangian relaxation and column generation; (2) provide two “where to go” strategies for both SMO and ETO; and (3) contribute to the mission of building safe and beneficial artificial general intelligence for manufacturing via evolutionary computation.

show abstract

Section: Discussionmentioning

confidence: 99%

Decomposition Is All You Need: Single-Objective to Multi-Objective Optimization towards Artificial General Intelligence

Xu,

Wang,

Guo

et al. 2023

Mathematics

View full text Add to dashboard Cite

show abstract

“…What does matter is the essence, not the superficies. For example, image super resolution [6], image caption and machine translation [15] may sound quite different at first sight, but they actually belong to the same issue when viewed from lens of theoretical generative deep learning(at least, when considering information preservation). So in the future, beyond vision, we may experimentally and theoretically explore two NLP tasks of image caption(a special task that bridges vision and NLP) and machine translation to reveal the veil of theoretical generative deep learning, contributing to the [14]science of intelligence.…”

Section: Theoretical Exploration In Generative Deep Learning In the Fmentioning

confidence: 99%

Theory of Generative Deep Learning II:Probe Landscape of Empirical Error via Norm Based Capacity Control

Zhang

2018

2018 5th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

View full text Add to dashboard Cite

Despite its remarkable empirical success as a highly competitive branch of artificial intelligence, deep learning is often blamed for its widely known low interpretation and lack of firm and rigorous mathematical foundation. However, most theoretical endeavor is devoted in discriminative deep learning case, whose complementary part is generative deep learning. To the best of our knowledge, we firstly highlight landscape of empirical error in generative case to complete the full picture through exquisite design of image super resolution under norm based capacity control. Our theoretical advance in interpretation of the training dynamic is achieved from both mathematical and biological sides.

show abstract

“…We abandon GAN for its less maturation. CNNs are more well studied and are widely used not only for vision, but also for audio, natural language processing (NLP) [8].…”

Section: Specified Architecture To Realize Warship: Convolutional Neumentioning

confidence: 99%

Towards WARSHIP: Combining Components of Brain-Inspired Computing of RSH for Image Super Resolution

Zhang

2018

2018 5th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

View full text Add to dashboard Cite

Evolution of deep learning shows that some algorithmic tricks are more durable , while others are not. To the best of our knowledge, we firstly summarize 5 more durable and complete deep learning components for vision, that is, WARSHIP. Moreover, we give a biological overview of WARSHIP, emphasizing brain-inspired computing of WARSHIP. As a step towards WARSHIP, our case study of image super resolution combines 3 components of RSH to deploy a CNN model of WARSHIP-XZNet, which performs a happy medium between speed and performance.

show abstract

A Content-Based Neural Reordering Model for Statistical Machine Translation

Cited by 7 publications

References 15 publications

Decomposition Is All You Need: Single-Objective to Multi-Objective Optimization towards Artificial General Intelligence

Decomposition Is All You Need: Single-Objective to Multi-Objective Optimization towards Artificial General Intelligence

Theory of Generative Deep Learning II:Probe Landscape of Empirical Error via Norm Based Capacity Control

Towards WARSHIP: Combining Components of Brain-Inspired Computing of RSH for Image Super Resolution

Contact Info

Product

Resources

About