On November 7, Nehal Hasnine from Hosei University in Tokyo visited Oliver Bendel at the FHNW Brugg-Windisch campus. Oliver Bendel wrote his doctoral thesis on pedagogical agents – chatbots, voice assistants, and early social robots in learning environments – at the University of St. Gallen at the turn of the millennium. In recent years, he and his students have developed chatbots and language assistants that support the learning and practicing of endangered languages. Nehal Hasnine is investigating the possibility of recommending appropriate images for vocabulary learning, geolocation-based word recommendation, clickstream analysis, ubiquitous log analysis, personalized learning path optimization, text mining for word concurrence information discovery, and topic modeling from life logs. According to his website, his expertise lies at the intersection of computer-aided language learning, foreign vocabulary learning, machine learning, image recommendation, data visualization, image analytics, and learning analytics. At the FHNW Brugg-Windisch campus, the two scientists presented their projects and discussed opportunities for collaboration.
Fig.: Oliver Bendel and Nehal Hasnine at the Swiss campus
The CONVERSATIONS 2023, a two-day workshop on chatbot research, applications, and design, will take place at the University of Oslo, Norway. According to the CfP, contributions concerning applications of large language models such as the GPT family, are warmly welcome, as are contributions on applications combining information retrieval approaches and large language model approaches. Building on the results from previous six CONVERSATIONS workshops, the following topics are of particular interest: 1. Chatbot users and implications, 2. Chatbot user experience, design, and evaluation, 3. Chatbot frameworks and platforms, 4. Chatbots for collaboration, 5. Democratizing chatbots – chatbots for all, 6. Ethics and safety implications of chatbots and large language models, 7. Leveraging advances in AI technology and large language models. More information via 2023.conversations.ws.
The Korean company Samsung Electronics announced new updates to its voice assistant Bixby that are designed to improve user experience, performance, and capabilities of the intelligent assistant and platform. One of the most interesting innovations concerns the voice of the users. According to Samsung, they „can personalize their Bixby Text Call voice“. „Using the new Bixby Custom Voice Creator, users can record different sentences for Bixby to analyze and create an AI generated copy of their voice and tone. Currently available in Korean, this generated voice is planned to be compatible with other Samsung apps beyond phone calls“ (Samsung, 22 February 2023). As early as 2017, Oliver Bendel wrote with respect to Adobe VoCo: „Today, just a few minutes of samples are enough to be able to imitate a speaker convincingly in all kinds of statements.“ In his article „The synthetization of human voices“, published in AI & Society, he also made ethical considerations. Now there seems to be a recognized market for such applications and they are being rolled out more widely.
On June 22, 2022, the paper „The SPACE THEA Project“ by Martin Spathelf and Oliver Bendel was published on arxiv.org. It was presented at the AAAI 2022 Spring Symposium „How Fair is Fair? Achieving Wellbeing AI“ at Stanford University and came in 2nd place in the Best Presentation Awards. From the abstract: „In some situations, no professional human contact can be available. Accordingly, one remains alone with one’s problems and fears. A manned Mars flight is certainly such a situation. A voice assistant that shows empathy and assists the astronauts could be a solution. In the SPACE THEA project, a prototype with such capabilities was developed using Google Assistant and Dialogflow Essentials. The voice assistant has a personality based on characteristics such as functional intelligence, sincerity, creativity, and emotional intelligence. It proves itself in seven different scenarios designed to represent the daily lives of astronauts, addressing operational crises and human problems. The paper describes the seven scenarios in detail, and lists technical and conceptual foundations of the voice assistant. Finally, the most important results are stated and the chapters are summarized.“ The paper will additionally be published in the proceedings volume of the symposium by the end of summer. It can be downloaded via arxiv.org/abs/2206.10390.
On February 18, 2022, the Dagstuhl Report „Conversational Agent as Trustworthy Autonomous System (Trust-CA)“ was published. Editors are Effie Lai-Chong Law, Asbjørn Følstad, Jonathan Grudin, and Björn Schuller. From the abstract: „This report documents the program and the outcomes of Dagstuhl Seminar 21381 ‚Conversational Agent as Trustworthy Autonomous System (Trust-CA)‘. First, we present the abstracts of the talks delivered by the Seminar’s attendees. Then we report on the origin and process of our six breakout (working) groups. For each group, we describe its contributors, goals and key questions, key insights, and future research. The themes of the groups were derived from a pre-Seminar survey, which also led to a list of suggested readings for the topic of trust in conversational agents. The list is included in this report for references.“ (Abstract Dagstuhl Report) The seminar, attended by scientists and experts from around the world, was held at Schloss Dagstuhl from September 19-24, 2022. The report can be downloaded via drops.dagstuhl.de/opus/volltexte/2022/15770/.
Fig.: The on-site group (Photo: Schloss Dagstuhl – LZ GmbH)
The paper „The SPACE THEA Project“ by Martin Spathelf and Oliver Bendel was accepted at the AAAI 2022 Spring Symposia (Stanford University). The two authors will present it at the end of March 2022 at the symposium „How Fair is Fair? Achieving Wellbeing AI“. From the abstract: „In some situations, no professional human contact can be available. Accordingly, one remains alone with one’s problems and fears. A manned Mars flight is certainly such a situation. A voice assistant that shows empathy and assists the astronauts could be a solution. In the SPACE THEA project, a prototype with such capabilities was developed using Google Assistant and Dialogflow Essentials. The voice assistant has a personality based on characteristics such as functional intelligence, sincerity, creativity, and emotional intelligence. It proves itself in seven different scenarios designed to represent the daily lives of astronauts, addressing operational crises and human problems. The paper describes the seven scenarios in detail, and lists technical and conceptual foundations of the voice assistant. Finally, the most important results are stated and the chapters are summarized.“ More information about the AAAI 2022 Spring Symposia is available here.
SPACE THEA was developd by Martin Spathelf at the School of Business FHNW from April to August 2021. The client and supervisor was Prof. Dr. Oliver Bendel. The voice assistant is supposed to show empathy and emotions towards astronauts on a Mars flight. Technically, it is based on Google Assistant and Dialogflow. The programmer chose a female voice with Canadian English. SPACE THEA’s personality includes functional and emotional intelligence, honesty, and creativity. She follows a moral principle: to maximize the benefit of the passengers of the spacecraft. The prototype was implemented for the following scenarios: conduct general conversations; help the user find a light switch; assist the astronaut when a thruster fails; greet and cheer up in the morning; fend off an insult for no reason; stand by a lonely astronaut; learn about the voice assistant. A video on the latter scenario is available here. Oliver Bendel has been researching conversational agents for 20 years. With his teams, he has developed 20 concepts and artifacts of machine ethics and social robotics since 2012.
