Yosuke Fukuchi

National Institute of Informatics

Most of agents that learn policy for tasks with reinforcement learning (RL) lack the ability to communicate with people, which makes human-agent collaboration challenging. We believe that, in order for RL agents to comprehend utterances from human colleagues, RL agents must infer the mental states that people attribute to them because people someti...

Humans sometimes attempt to infer an artificial agent’s mental state based on mere observations of its behavior. From the agent’s perspective, it is important to choose actions with awareness of how its behavior will be considered by humans. Previous studies have proposed computational methods to generate such publicly self-aware motion to allow an...

Intelligent agents (IAs) that use machine learning for decision-making often lack the explainability about what they are going to do, which makes human-IA collaboration challenging. However, previous methods of explaining IA behavior require IA developers to predefine vocabulary that expresses motion, which is problematic as IA decision-making beco...

For effective collaboration between humans and intelligent agents that employ machine learning for decision-making, humans must understand what agents can and cannot do to avoid over/under-reliance. A solution to this problem is adjusting human reliance through communication using reliance calibration cues (RCCs) to help humans assess agents' capab...

This study investigated how displaying a robot's attention heatmap while the robot point gesture at it influences human trust and acceptance of its outputs. We conducted an experiment using two types of visual tasks. In these tasks, the participants were required to decide whether to accept or reject the answers of an AI or robot. The participants...

This study used XAI, which shows its purposes and attention as explanations of its process, and investigated how these explanations affect human trust in and use of AI. In this study, we generated heat maps indicating AI attention, conducted Experiment 1 to confirm the validity of the interpretability of the heat maps, and conducted Experiment 2 to...

For effective collaboration between humans and intelligent agents that employ machine learning for decision-making, humans must understand what agents can and cannot do to avoid over/under-reliance. A solution to this problem is adjusting human reliance through communication using reliance calibration cues (RCCs) to help humans assess agents' capab...

When people are talking together in front of digital signage, advertisements that are aware of the context of the dialogue will work the most effectively. However, it has been challenging for computer systems to retrieve the appropriate advertisement from among the many options presented in large databases. Our proposed system, the Conversational C...

This study used XAI, which shows its purposes and attention as explanations of its process, and investigated how these explanations affect human trust in and use of AI. In this study, we generated heat maps indicating AI attention, conducted Experiment 1 to confirm the validity of the interpretability of the heat maps, and conducted Experiment 2 to...

This paper conducts the first trial to apply a masked language AI model and the "Gini coefficient" to the field of English study. We propose an algorithm named CLOZER that generates open cloze questions that inquiry knowledge of English learners. Open cloze questions (OCQ) have been attracting attention for both measuring the ability and facilitati...

User interfaces have been designed to fit typical users and their usage styles as assumed by designers. However, it is impossible to cover all the possible use cases. To address this problem, we propose Q-Mapping, which is a method for user interfaces to acquire the operation mapping, or mapping from user operations to their effects. Q -Mapping h...

We propose CASPER (ChAt, Shift and PERform), a novel dialog system consisting of three types of dialog models: chatter, shifter, and performer. Shifter, which is designed for topic switching, enables a seamless flow of dialog from open-domain chat- to task-oriented dialog. In a user study, CASPER gave a better impression in terms of naturalness of...

Open cloze questions have been attracting attention for both measuring the ability and facilitating the learning of L2 English learners. In spite of its benefits, the open cloze test has been introduced only sporadically on the educational front, largely because it is burdensome for teachers to manually create the questions. Unlike the more commonl...

Most natural-language-processing methods are designed for estimating context given an entire set of sentences at once. However, dialogue is incremental in nature. SCAIN (Simultaneous Contextualization and Interpretation) is an algorithm for incremental dialogue processing. Along with the progress of the dialogue, it can solve the interdependence pr...

Building an interactive artificial intelligence that can ask questions about the real world is one of the biggest challenges for vision and language problems. In particular, goal-oriented visual dialogue, where the aim of the agent is to seek information by asking questions during a turn-taking dialogue, has been gaining scholarly attention recentl...

Distributed representation of words has improved the performance for many natural language tasks. In many methods, however, only one meaning is considered for one label of a word, and multiple meanings of polysemous words depending on the context are rarely handled. Although research works have dealt with polysemous words, they determine the meanin...

In interactions, estimating how much information is being shared between participants is one of the crucial aspects that make the interaction more lively and enhance each participant's sense of understanding of the others. In this paper, we propose a model to estimate how much information is being shared between participants in a conversation. In t...

Agents that acquire their own policies autonomously have the risk of accidents caused by the agents’ unexpected behavior. Therefore, it is necessary to improve the predictability of the agents’ behavior in order to ensure the safety. Instruction-based Behavior Explanation (IBE) is a method for a reinforcement learning agent to announce the agent’s...

In cooperation, the workers must know how co-workers behave. However, an agent's policy, which is embedded in a statistical machine learning model, is hard to understand, and requires much time and knowledge to comprehend. Therefore, it is difficult for people to predict the behavior of machine learning robots, which makes Human Robot Cooperation c...