In this paper, we propose a dialogue model that reflects two important aspects of spoken dialogue system: to be robust' and to be cooperative'. For this purpose, our model has two main inference spaces: Conversational Space (CS) and Problem Solving Space (PSS). CS is a kind of dynamic Bayesian network that represents a meaning of utterance and general dialogue rule. Robust' aspect is treated in CS. PSS is a network so called Event Hierarchy that represents the structure of task domain problems. Cooperative' aspect is mainly treated in PSS. In constructing CS and making inference on PSS, system's process, from meaning understanding through response generation, is modeled by dividing into five steps. These steps are (1) meaning understanding, (2) intention understanding, (3) communicative effect, (4) reaction generation, and (5) response generation. Meaning understanding step constructs CS and response generation step composes a surface expression of system's response from the part of CS. Intention understanding step makes correspondence utterance type in CS with action in PSS. Reaction generation step selects a cooperative reaction in PSS and expands a reaction to utterance type of CS. The status of problem solving and declared user's preference are recorded in mental state by communicative effect step. Then from our point of view, cooperative problem solving dialogue is regarded as a process of constructing CS and achieving goal in PSS through these five steps.

In this paper, experimental results of evaluating dialogue strategies of confirmation with a noisy channel are presented. First, the types of errors in task-oriented dialogues are investigated and classified as communication, dialogue, knowledge, problem solving, or objective errors. Since the errors are of different levels, the methods for recovering from errors must be examined separately. We have investigated that the dialogue and knowledge errors generated by communication errors can be recovered through system confirmation with the user. In addition, we examined that the manner in which a system initiates dialogue, namely, dialogue strategies, might influence the cooperativity of their interactions depending on the frequency of confirmations and the amount of information conveyed. Furthermore, the choice of dialogue strategies will be influenced by the rate of occurrence of communication errors in a communication channel and related to the properties of the task, for example, the difficulty in achieving a goal or the frequency of the movement of initiatives. To verify these hypotheses, we prepared a testbed task, the Group Scheduling Task, and examined it through a computer-to-computer dialogue simulation in which one system took the part of a scheduling system and the other system acted as a user. In this simulation, erroneous input for the scheduling system was also developed. The user system was designed to act randomly so that it could simulate a real human user, while the scheduling system was devised to strictly follow a particular dialogue strategy of confirmation. The experimental results showed that a certain amount of confirmation was required to overcome errors when the rate of occurrence of communication errors was high, but that excessive confirmation did not serve to resolve errors, depending on the task involved.

We propose a new CALL (Computer-Assisted Language Learning) system for non-native learners of Japanese using speech recognition methods. The aim of the system is to help them develop natural pronunciation by automatically detecting their pronunciation errors and then providing effective feedback instruction. An automatic scoring method based on HMM log-likelihood is used to assess their pronunciation. Native speakers' scores are normalized by the mean and standard deviation for each phoneme and are used as threshold values to detect pronunciation errors. Unlike previous CALL systems, we not only detect pronunciation errors but also generate appropriate feedback to improve them. Especially for the feedback of consonants, we propose a novel method based on the classification of the place and manner of articulation. The effectiveness of our system is demonstrated with preliminary trials by several non-native speakers.

The Horn set is the set of Horn clauses. The Horn clause is the set of literals which contains at most one positive literal, where a positive literal means a literal without negation sign. The satisfiability problem of the Horn set in propositional logic is one of P-complete problems, although the satisfiability problem of the formula in propositional logic is one of typical NP-complete problems. In propositional logic, unit and input resolutions, proposed by C. L. Chang, are complete inference rules used to detect the satisfiability of the Horn set. In this paper, we formulate a Restricted Linear (RL) deduction, extending unit and input resolutions. The RL deduction is formed by layering linear deductions each of which corresponds to an input resolution refutation, and is called by another name, a Linear Layered Resolution deduction based on Input resolution (an LLRI deduction). Next, we formulate a Nonlinear Layered Resolution deduction based on Input resolutions (an NLRI deduction). By means of the LLRI and NLRI deductions, we propose some classes of extended Horn sets in propositional logic for which the satisfiability problems are solvable by LLRI and NLRI deductions in deterministic polynomial time; and, thus, so are P-complete. Also we propose algorithms to determine whether a given set of clauses is in the proposed classes of extended Horn sets.