scholarly journals Decoding Methods in Neural Language Generation: A Survey

Information ◽  
2021 ◽  
Vol 12 (9) ◽  
pp. 355
Author(s):  
Sina Zarrieß ◽  
Henrik Voigt ◽  
Simeon Schüz
Keyword(s):  
Neural Network ◽  
Search Space ◽  
Output Sequence ◽  
Language Generation ◽  
Survey Paper ◽  
Considerable Impact ◽  
Systematic Understanding ◽  
The Given ◽  
Broad Type ◽  
And Task

Neural encoder-decoder models for language generation can be trained to predict words directly from linguistic or non-linguistic inputs. When generating with these so-called end-to-end models, however, the NLG system needs an additional decoding procedure that determines the output sequence, given the infinite search space over potential sequences that could be generated with the given vocabulary. This survey paper provides an overview of the different ways of implementing decoding on top of neural network-based generation models. Research into decoding has become a real trend in the area of neural language generation, and numerous recent papers have shown that the choice of decoding method has a considerable impact on the quality and various linguistic properties of the generation output of a neural NLG system. This survey aims to contribute to a more systematic understanding of decoding methods across different areas of neural NLG. We group the reviewed methods with respect to the broad type of objective that they optimize in the generation of the sequence—likelihood, diversity, and task-specific linguistic constraints or goals—and discuss their respective strengths and weaknesses.

scholarly journals Influence of Personal and Task Interdependence on Task Conflict and Team Effectiveness

2016 ◽  
Vol 10 (4) ◽  
pp. 95 ◽  
Author(s):  
Jeffrey Lawrence D'Silva ◽  
Adriana Ortega ◽  
Abdul Hadi Sulaiman
Keyword(s):  
Team Effectiveness ◽  
Meta Analysis ◽  
Task Interdependence ◽  
Task Conflict ◽  
Personality Factors ◽  
Team Members ◽  
Information And Communication ◽  
The Subject ◽  
The Given ◽  
And Task

<p>Undeniably working in teams are important as tasks are getting more complicated and advanced as a result of globalization and the speedy growth of information and communication technology. This calls for effectiveness from team members to complete all interdependent sub-tasks to ensure that the given tasks achieve its’ desired objectives. During the process of implementing the tasks, teams are poised to face conflicts that may derail the completion of tasks. The focus of this paper is to examine the influence of personality factors and task interdependence on task conflict and team effectiveness. A meta-analysis on past studies was carried out to gather data on the subject matter. The input obtained will be pertinent for future researchers in further understanding the complexities associated with task interdependence and personality on task conflict and team effectiveness.</p>

scholarly journals Story Realization: Expanding Plot Events into Sentences

2020 ◽  
Vol 34 (05) ◽  
pp. 7375-7382
Author(s):  
Prithviraj Ammanabrolu ◽  
Ethan Tien ◽  
Wesley Cheung ◽  
Zhaochen Luo ◽  
William Ma ◽  
...  
Keyword(s):  
Neural Network ◽  
Natural Language ◽  
Human Subjects ◽  
Prior Work ◽  
Generation System ◽  
Language Generation ◽  
Story Generation ◽  
Sequence Of Events ◽  
End To End

Neural network based approaches to automated story plot generation attempt to learn how to generate novel plots from a corpus of natural language plot summaries. Prior work has shown that a semantic abstraction of sentences called events improves neural plot generation and and allows one to decompose the problem into: (1) the generation of a sequence of events (event-to-event) and (2) the transformation of these events into natural language sentences (event-to-sentence). However, typical neural language generation approaches to event-to-sentence can ignore the event details and produce grammatically-correct but semantically-unrelated sentences. We present an ensemble-based model that generates natural language guided by events. We provide results—including a human subjects study—for a full end-to-end automated story generation system showing that our method generates more coherent and plausible stories than baseline approaches 1.

Innovative Genetic Algorithmic Approach to Select Potential Patches Enclosing Real and Complex Zeros of Nonlinear Equation

2017 ◽  
Vol 6 (2) ◽  
pp. 18-37 ◽  
Author(s):  
Vijaya Lakshmi V. Nadimpalli ◽  
Rajeev Wankar ◽  
Raghavendra Rao Chillarige
Keyword(s):  
Genetic Algorithm ◽  
Nonlinear Equation ◽  
Complex Plane ◽  
Search Space ◽  
Regions Of Interest ◽  
Real Numbers ◽  
Algorithmic Approach ◽  
Space Reduction ◽  
Complex Zeros ◽  
The Given

In this article, an innovative Genetic Algorithm is proposed to find potential patches enclosing roots of real valued function f:R→R. As roots of f can be real as well as complex, the function is reframed on to complex plane by writing it as f(z). Thus, the problem now is transformed to finding potential patches (rectangles in C) enclosing z such that f(z)=0, which is resolved into two components as real and imaginary parts. The proposed GA generates two random populations of real numbers for the real and imaginary parts in the given regions of interest and no other initial guesses are needed. This is the prominent advantage of the method in contrast to various other methods. Additionally, the proposed ‘Refinement technique' aids in the exhaustive coverage of potential patches enclosing roots and reinforces the selected potential rectangles to be narrow, resulting in significant search space reduction. The method works efficiently even when the roots are closely packed. A set of benchmark functions are presented and the results show the effectiveness and robustness of the new method.

Modeling The Tower Of Hanoi Using Neural Network

1993 ◽  
pp. 47-56
Author(s):  
Mohamed Othman ◽  
Mohd. Hassan Selamat ◽  
Zaiton Muda ◽  
Lili Norliya Abdullah
Keyword(s):  
Neural Network ◽  
Knowledge Representation ◽  
Network Architecture ◽  
Learning Algorithm ◽  
Learning Rule ◽  
Neural System ◽  
Neural Systems ◽  
Tower Of Hanoi ◽  
Artificial Neural ◽  
The Given

This paper discusses the modeling of Tower of Hanoi using the concepts of neural network. The basis idea of backpropagation learning algorithm in Artificial Neural Systems is then described. While similar in some ways, Artificial Neural System learning deviates from tradition in its dependence on the modification of individual weights to bring about changes in a knowledge representation distributed across connection in a network. This unique form of learning is analyzed from two aspects: the selection of an appropriate network architecture for representing the problem, and the choice of a suitable learning rule capable qf reproducing the desired function within the given network. Key words: Tower of Hanoi; Backpropagation Algorithm; Knowledge Representation;

scholarly journals Design of optical meta-structures with applications to beam engineering using deep learning

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Robin Singh ◽  
Anu Agarwal ◽  
Brian W. Anthony
Keyword(s):  
Neural Network ◽  
Optimization Methods ◽  
Search Space ◽  
Global Optimum ◽  
Design Parameters ◽  
Diffraction Profile ◽  
Lab On Chip ◽  
Data Driven Approach ◽  
On Chip ◽  
Conventional Optimization

AbstractNanophotonics is a rapidly emerging field in which complex on-chip components are required to manipulate light waves. The design space of on-chip nanophotonic components, such as an optical meta surface which uses sub-wavelength meta-atoms, is often a high dimensional one. As such conventional optimization methods fail to capture the global optimum within the feasible search space. In this manuscript, we explore a Machine Learning (ML)-based method for the inverse design of the meta-optical structure. We present a data-driven approach for modeling a grating meta-structure which performs photonic beam engineering. On-chip planar photonic waveguide-based beam engineering offers the potential to efficiently manipulate photons to create excitation beams (Gaussian, focused and collimated) for lab-on-chip applications of Infrared, Raman and fluorescence spectroscopic analysis. Inverse modeling predicts meta surface design parameters based on a desired electromagnetic field outcome. Starting with the desired diffraction beam profile, we apply an inverse model to evaluate the optimal design parameters of the meta surface. Parameters such as the repetition period (in 2D axis), height and size of scatterers are calculated using a feedforward deep neural network (DNN) and convolutional neural network (CNN) architecture. A qualitative analysis of the trained neural network, working in tandem with the forward model, predicts the diffraction profile with a correlation coefficient as high as 0.996. The developed model allows us to rapidly estimate the desired design parameters, in contrast to conventional (gradient descent based or genetic optimization) time-intensive optimization approaches.

scholarly journals Design Space Exploration for YOLO Neural Network Accelerator

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1921
Author(s):  
Hongmin Huang ◽  
Zihao Liu ◽  
Taosheng Chen ◽  
Xianghong Hu ◽  
Qiming Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Design Space Exploration ◽  
Design Space ◽  
Space Exploration ◽  
Computation Time ◽  
Memory Bandwidth ◽  
Block Transmission ◽  
Transmission Strategy ◽  
The Neural Network ◽  
The Given

The You Only Look Once (YOLO) neural network has great advantages and extensive applications in computer vision. The convolutional layers are the most important part of the neural network and take up most of the computation time. Improving the efficiency of the convolution operations can greatly increase the speed of the neural network. Field programmable gate arrays (FPGAs) have been widely used in accelerators for convolutional neural networks (CNNs) thanks to their configurability and parallel computing. This paper proposes a design space exploration for the YOLO neural network based on FPGA. A data block transmission strategy is proposed and a multiply and accumulate (MAC) design, which consists of two 14 × 14 processing element (PE) matrices, is designed. The PE matrices are configurable for different CNNs according to the given required functions. In order to take full advantage of the limited logical resources and the memory bandwidth on the given FPGA device and to simultaneously achieve the best performance, an improved roofline model is used to evaluate the hardware design to balance the computing throughput and the memory bandwidth requirement. The accelerator achieves 41.99 giga operations per second (GOPS) and consumes 7.50 W running at the frequency of 100 MHz on the Xilinx ZC706 board.

Performance Analysis of a V2G Brokering Agent

2014 ◽  
Vol 686 ◽  
pp. 634-638 ◽  
Author(s):  
Jung Hoon Lee ◽  
Ji Hyun Kang
Keyword(s):  
Search Space ◽  
Stored Energy ◽  
Demand And Supply ◽  
Vehicle To Grid ◽  
Consumption Ratio ◽  
Available Energy ◽  
Power Load ◽  
Stay Time ◽  
Temporal And Spatial ◽  
The Given

This paper first presents a brokering architecture for a vehicle-to-grid electricity trades between electric vehicles and a microgrid, and then measures its performance, particularly focusing on the stay time, which significantly affects the scheduling flexibility. The brokering service matches demand and supply on battery-stored energy, traversing the search space to find an energy allocation for each time slot. The slot-by-slot schedule, generated from the two-way interaction protocol, coordinates the arrival time of each seller at the microgrid, achieving temporal and spatial power load shift. The performance measurement based on a prototype implementation analyzes the effect on the lacking and surplus energy, the demand meet ratio, and the effective consumption ratio. The experiment result shows that the brokering scheme can fully take advantage of enhanced flexibility in placing available energy on the time slots, reducing the lacking amount by up to 38.4 % as well as enhancing the consumption ratio by up to 27 % for the given parameter set.

Sign in / Sign up

Export Citation Format

Share Document