Kohji Dohsaka

Understanding Unsegmented User Utterances in Real-Time Spoken Dialogue Systems

This paper proposes a method for incrementally understanding user utterances whose semantic boundaries are not known and responding in real time even before boundaries are determined. It is an integrated parsing and discourse processing method that updates the partial result of understanding word by word, enabling responses based on the partial result. This method incrementally finds plausible sequences of utterances that play crucial roles in the task execution of dialogues, and utilizes beam search to deal with the ambiguity of boundaries as well as syntactic and semantic ambiguities. The results of a preliminary experiment demonstrate that this method understands user utterances better than an understanding method that assumes pauses to be semantic boundaries.

Analysis of Listening-Oriented Dialogue for Building Listening Agents

Our aim is to build listening agents that can attentively listen to the user and satisfy his/her desire to speak and have himself/herself heard. This paper investigates the characteristics of such listening-oriented dialogues so that such a listening process can be achieved by automated dialogue systems. We collected both listening-oriented dialogues and casual conversation, and analyzed them by comparing the frequency of dialogue acts, as well as the dialogue flows using Hidden Markov Models (HMMs). The analysis revealed that listening-oriented dialogues and casual conversation have characteristically different dialogue flows and that it is important for listening agents to self-disclose before asking questions and to utter more questions and acknowledgment than in casual conversation to be good listeners.

Effects of self-disclosure and empathy in human-computer dialogue

To build trust or cultivate long-term relationships with users, conversational systems need to perform social dialogue. To date, research has primarily focused on the overall effect of social dialogue in human-computer interaction, leading to little work on the effects of individual linguistic phenomena within social dialogue. This paper investigates such individual effects through dialogue experiments. Focusing on self-disclosure and empathic utterances (agreement and disagreement), we empirically calculate their contributions to the dialogue quality. Our analysis shows that (1) empathic utterances by users are strong indicators of increasing closeness and user satisfaction, (2) the systems empathic utterances are effective for inducing empathy from users, and (3) self-disclosure by users increases when users have positive preferences on topics being discussed.

Issues in predicting user satisfaction transitions in dialogues: individual differences, evaluation criteria, and prediction models

This paper addresses three important issues in automatic prediction of user satisfaction transitions in dialogues. The first issue concerns the individual differences in user satisfaction ratings and how they affect the possibility of creating a user-independent prediction model. The second issue concerns how to determine appropriate evaluation criteria for predicting user satisfaction transitions. The third issue concerns how to train suitable prediction models. We present our findings for these issues on the basis of the experimental results using dialogue data in two domains.

Fast reinforcement learning of dialogue policies using stable function approximation

We propose a method to speed up reinforcement learning of policies for spoken dialogue systems. This is achieved by combining a coarse grained abstract representation of states and actions with learning only in frequently visited states. The value of unsampled states is approximated by a linear interpolation of known states. Experiments show that the proposed method effectively optimizes dialogue strategies for frequently visited dialogue states.

WIT: A Toolkit for Building Robust and Real-Time Spoken Dialogu Systems

This paper describes WIT, a toolkit for building spoken dialogue systems. WIT features an incremental understanding mechanism that enables robust utterance understanding and realtime responses. WITs ability to compile domain-dependent system specifications into internal knowledge sources makes building spoken dialogue systems much easier than it is from scratch.

Building a conversational model from two-tweets

The current problem in building a conversational model from Twitter data is the scarcity of long conversations. According to our statistics, more than 90% of conversations in Twitter are composed of just two tweets. Previous work has utilized only conversations lasting longer than three tweets for dialogue modeling so that more than a single interaction can be successfully modeled. This paper verifies, by experiment, that two-tweet exchanges alone can lead to conversational models that are comparable to those made from longer-tweet conversations. This finding leverages the value of Twitter as a dialogue corpus and opens the possibility of better conversational modeling using Twitter data.

Learning to control listening-oriented dialogue using partially observable markov decision processes

Our aim is to build listening agents that attentively listen to their users and satisfy their desire to speak and have themselves heard. This article investigates how to automatically create a dialogue control component of such a listening agent. We collected a large number of listening-oriented dialogues with their user satisfaction ratings and used them to create a dialogue control component that satisfies users by means of Partially Observable Markov Decision Processes (POMDPs). Using a hybrid dialog controller where high-level dialog acts are chosen with a statistical policy and low-level slot values are populated by a wizard, we evaluated our dialogue control method in a Wizard-of-Oz experiment. The experimental results show that our POMDP-based method achieves significantly higher user satisfaction than other stochastic models, confirming the validity of our approach. This article is the first to verify, by using human users, the usefulness of POMDP-based dialogue control for improving user satisfaction in nontask-oriented dialogue systems.

Wizard of Oz evaluation of listening-oriented dialogue control using POMDP

We have been working on dialogue control for listening agents. In our previous study [1], we proposed a dialogue control method that maximizes user satisfaction using partially observable Markov decision processes (POMDPs) and evaluated it by a dialogue simulation. We found that it significantly outperforms other stochastic dialogue control methods. However, this result does not necessarily mean that our method works as well in real dialogues with human users. Therefore, in this paper, we evaluate our dialogue control method by a Wizard of Oz (WoZ) experiment. The experimental results show that our POMDP-based method achieves significantly higher user satisfaction than other stochastic models, confirming the validity of our approach. This paper is the first to show the usefulness of POMDP-based dialogue control using human users when the target function is to maximize user satisfaction.

A computational model of incremental utterance production in task-oriented dialogues

This paper presents a computational model of incremental utterance production in task-oriented dialogues. This model incrementally produces utterances to propose the solution of a given problem, while simultanceously solving the problem in a stepwise manner. Even when the solution has been partially determined, this model starts utterances to satisfy time constraints where pauses in mid-utterance must not exceed a certain length. The results of an analysis of discourse structure in a dialogue corpus are presented and the fine structure of discourse that contributes to the incremental strategy of utterance production is described. This model utilizes such a discourse structure to incrementally produce utterances constituting a discourse. Pragmatic constraints are exploited to guarantee the relevance of discourses, which are evaluated by an utterance simulation experiment.