This paper presents a taxonomy of errors in chat-oriented dialogue systems. Compared to human-human conversations and task-oriented dialogues, little is known about the errors made in chat-oriented dialogue systems. Through a data collection of chat dialogues and analyses of dialogue breakdowns, we classified errors and created a taxonomy. Although the proposed taxonomy may not be complete, this paper is the first to present a taxonomy of errors in chat-oriented dialogue systems. We also highlight the difficulty in pinpointing errors in such systems.
This paper aims to find errors that lead to dialogue breakdowns in chat-oriented dialogue systems. We collected chat dialogue data, annotated them with dialogue breakdown labels, and collected comments describing the error that led to the breakdown. By mining the comments, we first identified error types. Then, we calculated the correlation between an error type and the degree of dialogue breakdown it incurred, quantifying its impact on dialogue breakdown. This is the first study to quantitatively analyze error types and their effect in chat-oriented dialogue systems.
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 system's 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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.