No abstract

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.

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.

Abstract-Automatic speech recognition (ASR) and Text to speech (TTS) are two prominent area of research in human computer interaction nowadays. A set of phonetically rich sentences is in a matter of importance in order to develop these two interactive modules of HCI. Essentially, the set of phonetically rich sentences has to cover all possible phone units distributed uniformly. Selecting such a set from a big corpus with maintaining phonetic characteristic based similarity is still a challenging problem. The major objective of this paper is to devise a criteria in order to select a set of sentences encompassing all phonetic aspects of a corpus with size as minimum as possible. First, this paper presents a statistical analysis of Hindi phonetics by observing the structural characteristics. Further a two stage algorithm is proposed to extract phonetically rich sentences with a high variety of triphones from the EMILLE Hindi corpus. The algorithm consists of a distance measuring criteria to select a sentence in order to improve the triphone distribution. Moreover, a special preprocessing method is proposed to score each triphone in terms of inverse probability in order to fasten the algorithm. The results show that the approach efficiently build uniformly distributed phonetically-rich corpus with optimum number of sentences.

No abstract