A Collaborative Multi-agent Reinforcement Learning Framework for Dialog Action Decomposition

Most reinforcement learning methods for dialog policy learning train a centralized agent that selects a predefined joint action concatenating domain name, intent type, and slot name. The centralized dialog agent suffers from a great many user-agent interaction requirements due to the large action space. Besides, designing the concatenated actions is laborious to engineers and maybe struggled with edge cases. To solve these problems, we model the dialog policy learning problem with a novel multi-agent framework, in which each part of the action is led by a different agent. The framework reduces labor costs for action templates and decreases the size of the action space for each agent. Furthermore, we relieve the non-stationary problem caused by the changing dynamics of the environment as evolving of agents' policies by introducing a joint optimization process that makes agents can exchange their policy information. Concurrently, an independent experience replay buffer mechanism is integrated to reduce the dependence between gradients of samples to improve training efficiency. The effectiveness of the proposed framework is demonstrated in a multi-domain environment with both user simulator evaluation and human evaluation.

Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition

We present a fast and scalable architecture called Explicit Modular Decomposition (EMD), in which we incorporate both classification-based and extraction-based methods and design four modules (for clas- sification and sequence labelling) to jointly extract dialogue states. Experimental results based on the MultiWoz 2.0 dataset validates the superiority of our proposed model in terms of both complexity and scalability when compared to the state-of-the-art methods, especially in the scenario of multi-domain dialogues entangled with many turns of utterances.

Chinese Character Decomposition for Neural MT with Multi-Word Expressions

Chinese character decomposition has been used as a feature to enhance Machine Translation (MT) models, combining radicals into character and word level models. Recent work has investigated ideograph or stroke level embedding. However, questions remain about different decomposition levels of Chinese character representations, radical and strokes, best suited for MT. To investigate the impact of Chinese decomposition embedding in detail, i.e., radical, stroke, and intermediate levels, and how well these decompositions represent the meaning of the original character sequences, we carry out analysis with both automated and human evaluation of MT. Furthermore, we investigate if the combination of decomposed Multiword Expressions (MWEs) can enhance the model learning. MWE integration into MT has seen more than a decade of exploration. However, decomposed MWEs has not previously been explored.

Numerical Solution of Some Important Models of Partial Differential Equations Using Approximate - Analytical Methods ( ADM – VIM )

In this article, powerful approximate analytical methods, called Adomian decomposition method and variational iteration method are introduced and applied to obtaining the approximate analytical solutions for an important models of linear and non-linear partial differential equations such as ( nonlinear Klein Gordon equation - nonlinear wave equation - linear telegraph equation - nonlinear diffusion convection equation ) . The studied examples are used to reveal that those methods are very effective and convenient for solving linear and nonlinear partial differential equations . Numerical results and comparisons with the exact solution are included to show validity, ability, accuracy, strength and effectiveness of those techniques.

Comparison of Some LU-factorization Methods for Solving pentadiagonal Linear Systems of Equations

In this Searching scientific, , we introduced three methods for finding the solution of pentadiagonal linear systems of equations.

Studying the Relationship Between hydrocarbons Saturation and Frequency Domain With Continuous Wavelet Transform (CWT)

Low frequency shadows is one of hydrocarbons indicators. It can be detected by means of a time-frequency decomposition which can provide higher frequency resolution at lower frequencies and higher time resolution at higher frequencies. This is desirable for analyzing seismic data, because the hydrocarbons in reservoir are diagnostic at lower frequencies. we have carried out such analyses with post-stack data sets on Fahda field which is located in Aleppo uplift, it contains oil. Adding a frequency axis to a 2D seismic section makes the data 3D axis. The comparison of the single frequency sections from such 3D volume can be utilized to detect low frequency shadows. A preferentially illuminated single frequency section at lower frequencies from Fahda field, shows high amplitude low frequency anomalies beneath oil zones. These anomalies disappear at higher frequencies.