International Workshop on Spoken Dialogue Systems Technology最新文献

Understanding How People Rate Their Conversations 了解人们如何评价他们的谈话

International Workshop on Spoken Dialogue Systems Technology Pub Date : 2022-06-01 DOI: 10.48550/arXiv.2206.00167

A. Papangelis, Nicole Chartier, Pankaj Rajan, J. Hirschberg, Dilek Z. Hakkani-Tür

{"title":"Understanding How People Rate Their Conversations","authors":"A. Papangelis, Nicole Chartier, Pankaj Rajan, J. Hirschberg, Dilek Z. Hakkani-Tür","doi":"10.48550/arXiv.2206.00167","DOIUrl":"https://doi.org/10.48550/arXiv.2206.00167","url":null,"abstract":"User ratings play a signiﬁcant role in spoken dialogue systems. Typically, such ratings tend to be averaged across all users and then utilized as feedback to improve the system or personalize its behavior. While this method can be useful to understand broad, general issues with the system and its behavior, it does not take into account differences between users that affect their ratings. In this work, we conduct a study to better understand how people rate their interactions with conversational agents. One macro-level characteristic that has been shown to cor-relate with how people perceive their inter-personal communication is personality [1, 2, 12]. We speciﬁcally focus on agreeableness and extraversion as variables that may explain variation in ratings and therefore provide a more meaningful signal for training or personalization. In order to elicit those personality traits during an interaction with a conversational agent, we designed and validated a ﬁctional story, grounded in prior work in psychology. We then implemented the story into an experimental conversational agent that allowed users to opt-in to hearing the story. Our results suggest that for human-conversational agent interactions, extraversion may play a role in user ratings, but more data is needed to determine if the relationship is signiﬁcant. Agreeableness, on the other hand, plays a statistically signiﬁcant role in conversation ratings: users who are more agreeable are more likely to provide a higher rating for their interaction. In addition, we found that users who opted to hear the story were, in general, more likely to rate their conversational experience higher than those who did not.","PeriodicalId":200919,"journal":{"name":"International Workshop on Spoken Dialogue Systems Technology","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133260592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Design Guidelines for Developing Systems for Dialogue System Competitions 开发对话系统竞赛系统的设计指南

International Workshop on Spoken Dialogue Systems Technology Pub Date : 2022-05-01 DOI: 10.1527/tjsai.37-3_ids-b

Kazunori Komatani, Ryu Takeda, Keisuke Nakashima, Mikio Nakano

引用次数: 1

Jurassic is (almost) All You Need: Few-Shot Meaning-to-Text Generation for Open-Domain Dialogue 侏罗纪(几乎)是你所需要的:为开放领域对话生成少量的意义到文本

International Workshop on Spoken Dialogue Systems Technology Pub Date : 2021-10-15 DOI: 10.1007/978-981-19-5538-9_7

Lena Reed, Cecilia Li, Angela Ramirez, Liren Wu, M. Walker

引用次数: 5

Investigating the Impact of Pre-trained Language Models on Dialog Evaluation 研究预训练语言模型对对话评价的影响

International Workshop on Spoken Dialogue Systems Technology Pub Date : 2021-10-05 DOI: 10.1007/978-981-19-5538-9_21

Chen Zhang, L. F. D’Haro, Yiming Chen, Thomas Friedrichs, Haizhou Li

引用次数: 5

Towards Handling Unconstrained User Preferences in Dialogue 在对话中处理不受约束的用户偏好

International Workshop on Spoken Dialogue Systems Technology Pub Date : 2021-09-17 DOI: 10.1007/978-981-19-5538-9_6

S. Pandey, Svetlana Stoyanchev, R. Doddipatla

引用次数: 2

Empathetic Dialogue Generation with Pre-trained RoBERTa-GPT2 and External Knowledge 用预训练的RoBERTa-GPT2和外部知识生成共情对话

International Workshop on Spoken Dialogue Systems Technology Pub Date : 2021-09-07 DOI: 10.1007/978-981-19-5538-9_5

Ye Liu, Wolfgang Maier, W. Minker, Stefan Ultes

引用次数: 8

Out-of-Scope Domain and Intent Classification through Hierarchical Joint Modeling 基于层次关节建模的范围外域和意图分类

International Workshop on Spoken Dialogue Systems Technology Pub Date : 2021-04-30 DOI: 10.1007/978-981-19-5538-9_1

Peng Liu, Kun Li, H. Meng

引用次数: 0

How to Address Humans: System Barge-In in Multi-user HRI 如何解决人类:多用户HRI中的系统驳船

International Workshop on Spoken Dialogue Systems Technology Pub Date : 2021-03-11 DOI: 10.1007/978-981-15-9323-9_13

Nicolas Wagner, Matthias Kraus, Niklas Rach, W. Minker

引用次数: 5

Conversational Systems Research in Spain: A Scientometric Approach 会话系统研究在西班牙:科学计量方法

International Workshop on Spoken Dialogue Systems Technology Pub Date : 2020-10-25 DOI: 10.1007/978-981-15-8395-7_31

D. Griol, Zoraida Callejas Carrión

引用次数: 0

A Spanish Corpus for Talking to the Elderly 与老人交谈的西班牙语语料库

International Workshop on Spoken Dialogue Systems Technology Pub Date : 2020-10-25 DOI: 10.1007/978-981-15-8395-7_13

R. Justo, Leila Ben Letaifa, J. M. Olaso, Asier López-Zorrilla, M. deVelasco, A. Vázquez, M. I. Torres

引用次数: 3