Expressing Coherent Personality with Incremental Acquisition of Multimodal Behaviors

Mota, Pedro; Paetzel, Maike; Fox, Andrea; Amini, Aida; Srinivasan, Siddarth; Kennedy, James

doi:10.1109/roman.2018.8525763

Cited by 8 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In previous work, we showed that crowd-authoring can be used to create personality-driven conversational content for a robot playing a cooperative game Mota et al (2018). We designed two personalities similar to those presented in this paper: one that was quick to overreact and had little patience for life's imperfections, the other that was lighthearted, optimistic, and determined to find the fun in every situation.…”

Section: Conversational Contentmentioning

confidence: 99%

See 1 more Smart Citation

The Influence of robot personality on the development of uncanny feelings

Paetzel-Prüsmann

Perugia

Castellano

2021

Computers in Human Behavior

View full text Add to dashboard Cite

Section: Conversational Contentmentioning

confidence: 99%

“…Crowd-Authoring content Following the approach introduced in our previous research (Mota et al, 2018;Paetzel, Kennedy, Castellano, & Lehman, 2018), we asked crowd-workers on Amazon Mechanical Turk to author affective content for our robot. The crowd-sourcing pipeline consisted of three stages.…”

Section: Conversational Contentmentioning

confidence: 99%

The Influence of robot personality on the development of uncanny feelings

Paetzel-Prüsmann

Perugia

Castellano

2021

Computers in Human Behavior

View full text Add to dashboard Cite

“…Emotion depends on individual users, e.g., their personality traits (such as the Big Five (Goldberg, 1990)). Personality traits also play an important role in a variety of user-adapted interactions (Mairesse and Walker, 2010;Mota et al, 2018;Fernau et al, 2022;Yamamoto et al, 2023). The personality traits of a robot and human interlocutors are known to be effective for engagement estimation in human-robot interactions (Salam et al, 2017), and correlation between the engagement and the personality traits given per dialogue has been investigated in human-robot and human-human interactions (Celiktutan et al, 2019).…”

Section: Related Workmentioning

confidence: 99%

Analyzing Differences in Subjective Annotations by Participants and Third-party Annotators in Multimodal Dialogue Corpus

Komatani,

Takeda,

Okada

2023

Proceedings of the 24th Meeting of the Special Interest Group on Discourse and Dialogue

View full text Add to dashboard Cite

Estimating the subjective impressions of human users during a dialogue is necessary when constructing a dialogue system that can respond adaptively to their emotional states. However, such subjective impressions (e.g., how much the user enjoys the dialogue) are inherently ambiguous, and the annotation results provided by multiple annotators do not always agree because they depend on the subjectivity of the annotators. In this paper, we analyzed the annotation results using 13,226 exchanges from 155 participants in a multimodal dialogue corpus called Hazumi that we had constructed, where each exchange was annotated by five third-party annotators. We investigated the agreement between the subjective annotations given by the third-party annotators and the participants themselves, on both perexchange annotations (i.e., participant's sentiments) and per-dialogue (-participant) annotations (i.e., questionnaires on rapport and personality traits). We also investigated the conditions under which the annotation results are reliable. Our findings demonstrate that the dispersion of third-party sentiment annotations correlates with agreeableness of the participants, one of the Big Five personality traits.

show abstract

“…Our pipeline to collect crowd-sourced ratings of dialogue lines follows the approach described by Mota et al (2018) with few alterations. In the first evaluation stage, a set of untrained crowd-workers are asked to judge how typical and ordinary a sentence is given a situational description and how offensive it is on a five-point Likert scale.…”

Section: A Crowd-sourced Human Evaluation Pipelinementioning

confidence: 99%

“…Initially, we used a crowd-authoring technique to gather potential responses for our dialogue agent (Mota et al, 2018). It has previously been shown that such crowd-authored content helps achieve variety in a dialogue system's responses (Wang et al, 2012;Mitchell et al, 2014;Shah et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Estimating Subjective Crowd-Evaluations as an Additional Objective to Improve Natural Language Generation

Nyberg,

Manuvinakurike,

Paetzel-Prüsmann

2021

Preprint

View full text Add to dashboard Cite

Human ratings are one of the most prevalent methods to evaluate the performance of natural language processing algorithms. Similarly, it is common to measure the quality of sentences generated by a natural language generation model using human raters. In this paper, we argue for exploring the use of subjective evaluations within the process of training language generation models in a multi-task learning setting. As a case study, we use a crowdauthored dialogue corpus to fine-tune six different language generation models. Two of these models incorporate multi-task learning and use subjective ratings of lines as part of an explicit learning goal. A human evaluation of the generated dialogue lines reveals that utterances generated by the multi-tasking models were subjectively rated as the most typical, most moving the conversation forward, and least offensive. Based on these promising first results, we discuss future research directions for incorporating subjective human evaluations into language model training and to hence keep the human user in the loop during the development process.

show abstract

Expressing Coherent Personality with Incremental Acquisition of Multimodal Behaviors

Cited by 8 publications

References 19 publications

The Influence of robot personality on the development of uncanny feelings

The Influence of robot personality on the development of uncanny feelings

Analyzing Differences in Subjective Annotations by Participants and Third-party Annotators in Multimodal Dialogue Corpus

Estimating Subjective Crowd-Evaluations as an Additional Objective to Improve Natural Language Generation

Contact Info

Product

Resources

About