In recent years reinforcement-learning-based approaches have been widely used for management policy optimization in spoken dialogue systems (SDS). A dialogue management policy is a mapping from dialogue states to system actions, i.e. given the state of the dialogue the dialogue policy determines the next action to be performed by the dialogue manager. So-far policy optimization primarily focuse...

Reinforcement Learning (RL) algorithms are particularly well suited to some of the challenges of spoken dialogue systems (SDS) design. RL provides an approach for automated learning that can adapt to new environments without supervision. SDS are constantly subjected to new environments in the form of new groups of users, and developer intervention is costly. In this paper, I will describe some ...

This study investigated the effect of oral dialogue journals on communicative competence of Iranian EFL learners. Participants of this study were 80 students of two Payam-e-Noor Universities who were proved to be homogenous in the communicative competence based on TSE (Test of Spoken English) interview. The participants of one of these universities were considered as the experimental group. The...

Due to the relatively simple structure of dialogues in previous spoken dialogue systems, discourse structure has seen limited applications in these systems. We investigate the utility of discourse structure for spoken dialogue systems in complex domains (e.g. tutoring). Two types of applications are being pursued: on the system side and on the user side. On the system side, we investigate if th...

We propose a non-humanlike spoken dialogue design, which consists of two elements: non-humanlike turn-taking and non-humanlike acknowledgment. Two experimental studies are reported in this paper. The first study shows that the proposed non-humanlike spoken dialogue design is effective for reducing speech collisions. It also presents pieces of evidence that show quick humanlike turn-taking is le...

In spoken dialogue systems, robust language processing for spontaneous speech understanding and robust dialogue processing for achieving user goal are inevitable. Previously, research of speech recognition and research of natural language understanding were done independently. At first glance, it seems to be no problem to combine these two technologies, because the purpose of speech recognition...

We hypothesize that monitoring the accuracy of the “feeling of another’s knowing” (FOAK) is a useful predictor of tutorial dialogue system performance. We test this hypothesis in the context of a wizarded spoken dialogue tutoring system, where student learning is the primary performance metric. We first present our corpus, which has been annotated with respect to student correctness and uncerta...

We report on a novel approach to generating strategies for spoken dialogue systems. We present a series of experiments that illustrate how an evolutionary reinforcement learning algorithm can produce strategies that are both optimal and easily inspectable by human developers. Our experimental strategies achieve a mean performance of 98.9% with respect to a predefined evaluation metric. Our appr...

Human interaction with spoken dialogue systems differ in many ways from their interactions with each other. One notable example is that spoken dialogue systems tend to have a strict concept of turns which makes the dialogue more similar to a ping-pong game than to humans conversing. Given that we aim at creating spoken dialogue systems that can engage in human-like conversation (note that altho...

In this paper, we propose a new method to expand an examplebased spoken dialogue system to handle context dependent utterances. The dialogue system refers to the dialogue examples to find an example that is suitable to promote dialogue. Here, the dialogue contexts are expressed in the form of dialogue slots. By constructing dialogue examples with the text of utterances and the dialogue slots, t...