In this paper, an extended combined approach of phrase based statistical machine translation (SMT), example based MT (EBMT) and rule based MT (RBMT) is proposed to develop a novel hybrid data driven MT system capable of outperforming the baseline SMT, EBMT and RBMT systems from which it is derived. In short, the proposed hybrid MT process is guided by the rule based MT after getting a set of partial candidate translations provided by EBMT and SMT subsystems. Previous works have shown that EBMT systems are capable of outperforming the phrase-based SMT systems and RBMT approach has the strength of generating structurally and morphologically more accurate results. This hybrid approach increases the fluency, accuracy and grammatical precision which improve the quality of a machine translation system. A comparison of the proposed hybrid machine translation (HTM) model with renowned translators i.e. Google, BING and Babylonian is also presented which shows that the proposed model works better on sentences with ambiguity as well as comprised of idioms than others.
27 December 2007 in EURASIP Journal on Advances in Signal Processing
We present an adaptively accelerated Lucy-Richardson (AALR) method for the restoration of an image from its blurred and noisy version. The conventional Lucy-Richardson (LR) method is nonlinear and therefore its convergence is very slow. We present a novel method to accelerate the existing LR method by using an exponent on the correction ratio of LR. This exponent is computed adaptively in each iteration, using first-order derivatives of the deblurred image from previous two iterations. Upon using this exponent, the AALR improves speed at the first stages and ensures stability at later stages of iteration. An expression for the estimation of the acceleration step size in AALR method is derived. The superresolution and noise amplification characteristics of the proposed method are investigated analytically. Our proposed AALR method shows better results in terms of low root mean square error (RMSE) and higher signal-to-noise ratio (SNR), in approximately 43% fewer iterations than those required for LR method. Moreover, AALR method followed by wavelet-domain denoising yields a better result than the recently published state-of-the-art methods.
25 May 2022 in ACM Transactions on Asian and Low-Resource Language Information Processing
Dialogue policy is a crucial component in task-oriented Spoken Dialogue Systems (SDSs). As a decision function, it takes the current dialogue state as input and generates appropriate system’s response. In this paper, we explore the reinforcement learning approaches to solve this problem in an Indic language scenario. Recently, Deep Reinforcement Learning (DRL) has been used to optimise the dialogue policy. However, many DRL approaches are not sample-efficient. Hence, particular attention is given to actor-critic methods based on off-policy reinforcement learning that utilise the Experience Replay (ER) technique for reducing the bias and variance to achieve high sample efficiency. ER based actor-critic methods, such as Advantage Actor-Critic Experience Replay (A2CER) are proven to deliver competitive results in gaming environments that are fully observable and have a very small action-set. While, in SDSs, the states are not fully observable and often have to deal with the large action space. Describing the limitations of traditional methods, i.e., value-based and policy-based methods, such as high variance, low sample-efficiency, and often converging to local optima, we firstly explore the use of A2CER in dialogue policy learning. It is shown to beat the current state-of-the-art deep learning methods for SDS. Secondly, to handle the issues of early-stage performance, we utilise a demonstration corpus to pre-train the models prior to on-line policy learning. We thus experiment with the A2CER on a larger action space and find it significantly faster than the current state-of-the-art. Combining both approaches, we present a novel DRL based dialogue policy optimisation method, A2CER and its effectiveness for a task-oriented SDS in the Indic language.