CNR Author
operator:
and / or
Typology
operator:
and / or
Language
operator:
and / or
Date
operator:
and / or
Rights
operator:
and / or
2023
Conference article
Open Access
Towards a chatbot for creating trigger-action rules based on ChatGPT and Rasa
Gallo S., Malizia A., Paternò F.
In this paper, we propose a novel approach for building a conversational agent for creating trigger-action rules and controlling smart objects inside smart environments, such as a smart home. Our approach integrates ChatGPT, a state-of-the-art pre-trained language model for open-domain dialogue generation, with Rasa, a popular open-source framework for developing task-oriented chatbots. We leverage ChatGPT's abilities to perform Natural Language Processing tasks through prompting and few-shot learning, and Rasa Open Source's features to handle intents, entities, forms, and execute actions. We design Rasa custom actions that invoke ChatGPT's API to process complex customization rules, manage conversational breakdowns and answer questions about the smart environment.Source: EMPATHY 2023 - 4th International Workshop on Empowering People in Dealing with Internet of Things Ecosystems, Cagliari, Italy, 06/06/2023
Gallo S., Malizia A., Paternò F.
In this paper, we propose a novel approach for building a conversational agent for creating trigger-action rules and controlling smart objects inside smart environments, such as a smart home. Our approach integrates ChatGPT, a state-of-the-art pre-trained language model for open-domain dialogue generation, with Rasa, a popular open-source framework for developing task-oriented chatbots. We leverage ChatGPT's abilities to perform Natural Language Processing tasks through prompting and few-shot learning, and Rasa Open Source's features to handle intents, entities, forms, and execute actions. We design Rasa custom actions that invoke ChatGPT's API to process complex customization rules, manage conversational breakdowns and answer questions about the smart environment.Source: EMPATHY 2023 - 4th International Workshop on Empowering People in Dealing with Internet of Things Ecosystems, Cagliari, Italy, 06/06/2023
See at:
ceur-ws.org 
| ISTI Repository | CNR ExploRA
2023
Conference article
Open Access
Supporting users in controlling automations in intelligent environments through conversational agents
Gallo S.
The integration of sensors and intelligent devices in everyday environments is changing the way people interact with common objects. The need to provide non-expert users with an easy and efficient way to customize the behaviour of these devices according to their preferences and habits is crucial. This paper presents the work carried out by the author in the development of a conversational agent to empower the end-user in controlling intelligent environments, allowing for easy and fast communication with sensors, actuators, and smart objects using trigger-action customisation rules. The paper provides an overview of the state of the art in research and commercial solutions for conversational agents and presents some preliminary results of the research. Then, the ongoing work on a Systematic Literature Review and the migration to open-source solutions are presented. Finally, an overview of future work is given.Source: EMPATHY 2023 - 4th International Workshop on Empowering People in Dealing with Internet of Things Ecosystems, Cagliari, Italy, 06/06/2023
Gallo S.
The integration of sensors and intelligent devices in everyday environments is changing the way people interact with common objects. The need to provide non-expert users with an easy and efficient way to customize the behaviour of these devices according to their preferences and habits is crucial. This paper presents the work carried out by the author in the development of a conversational agent to empower the end-user in controlling intelligent environments, allowing for easy and fast communication with sensors, actuators, and smart objects using trigger-action customisation rules. The paper provides an overview of the state of the art in research and commercial solutions for conversational agents and presents some preliminary results of the research. Then, the ongoing work on a Systematic Literature Review and the migration to open-source solutions are presented. Finally, an overview of future work is given.Source: EMPATHY 2023 - 4th International Workshop on Empowering People in Dealing with Internet of Things Ecosystems, Cagliari, Italy, 06/06/2023
See at:
ceur-ws.org | ISTI Repository | CNR ExploRA
2023
Conference article
Open Access
Galliz at GeoLingIt: enhancing BERT with vocabulary knowledge for predicting the region of language varieties of Italy
Labruna T., Gallo S.
The linguistic diversity of the Italian peninsula and its islands, characterized by several language varieties, represents a linguistic condition and a cultural treasure unique in Europe. However, the oral nature of these varieties poses a challenge to their preservation in the written form. While significant research efforts have been dedicated to standard Italian language processing, less attention has been given to the language varieties of Italy and the development of supporting resources. This paper aims to study the peculiarities of language varieties of Italy and identify the region of origin of tweets written in non-[Standard Italian] varieties. To achieve this goal, we utilized two main techniques: fine-tuning a language model (BERT) and implementing an algorithm that utilizes dictionaries of regional varieties and word frequency. Our results show that integrating lexical analysis with BERT could be a promising approach for this particular task. We present an overview of the data, methodology, and evaluation results, then discuss the implications of our findings.Source: EVALITA 2023 - Eighth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian, Parma, Italy, 07-08/08/2023
Labruna T., Gallo S.
The linguistic diversity of the Italian peninsula and its islands, characterized by several language varieties, represents a linguistic condition and a cultural treasure unique in Europe. However, the oral nature of these varieties poses a challenge to their preservation in the written form. While significant research efforts have been dedicated to standard Italian language processing, less attention has been given to the language varieties of Italy and the development of supporting resources. This paper aims to study the peculiarities of language varieties of Italy and identify the region of origin of tweets written in non-[Standard Italian] varieties. To achieve this goal, we utilized two main techniques: fine-tuning a language model (BERT) and implementing an algorithm that utilizes dictionaries of regional varieties and word frequency. Our results show that integrating lexical analysis with BERT could be a promising approach for this particular task. We present an overview of the data, methodology, and evaluation results, then discuss the implications of our findings.Source: EVALITA 2023 - Eighth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian, Parma, Italy, 07-08/08/2023
See at:
ceur-ws.org | ISTI Repository | CNR ExploRA
2023
Conference article
Open Access
Conversational interfaces in IoT ecosystems: where we are, what is still missing
Gallo S., Paternò F., Malizia A.
In the last few years, text and voice-based conversational agents have become more and more popular all over the world as virtual assistants for a variety of tasks. In addition, the deployment on the market of many smart objects connected with these agents has introduced the possibility of controlling and personalising the behaviour of several connected objects using natural language. This has the potential to allow people, also those without a technical background, to effectively control and use the wide variety of connected objects and services. In this paper, we present an analysis of how conversational agents have been used to interact with smart environments (such as smart homes). For this purpose, we have carried out a systematic literature review considering publications selected from the ACM and IEEE digital libraries to investigate the technologies used to design and develop conversational agents for IoT settings, including Artificial Intelligence techniques, the purpose that they have been used for, and the level of user involvement in such studies. The resulting analysis is useful to better understand how this field is evolving and indicate the challenges still open in this area that should be addressed in future research work to allow people to completely benefit from this type of solution.Source: MUM '23: 22nd International Conference on Mobile and Ubiquitous Multimedia, pp. 279–293, Vienna, Austria, 3-6/12/2023
DOI: 10.1145/3626705.3627775
Metrics:
Gallo S., Paternò F., Malizia A.
In the last few years, text and voice-based conversational agents have become more and more popular all over the world as virtual assistants for a variety of tasks. In addition, the deployment on the market of many smart objects connected with these agents has introduced the possibility of controlling and personalising the behaviour of several connected objects using natural language. This has the potential to allow people, also those without a technical background, to effectively control and use the wide variety of connected objects and services. In this paper, we present an analysis of how conversational agents have been used to interact with smart environments (such as smart homes). For this purpose, we have carried out a systematic literature review considering publications selected from the ACM and IEEE digital libraries to investigate the technologies used to design and develop conversational agents for IoT settings, including Artificial Intelligence techniques, the purpose that they have been used for, and the level of user involvement in such studies. The resulting analysis is useful to better understand how this field is evolving and indicate the challenges still open in this area that should be addressed in future research work to allow people to completely benefit from this type of solution.Source: MUM '23: 22nd International Conference on Mobile and Ubiquitous Multimedia, pp. 279–293, Vienna, Austria, 3-6/12/2023
DOI: 10.1145/3626705.3627775
Metrics:
See at:
dl.acm.org | ISTI Repository | CNR ExploRA
2022
Conference article
Open Access
A conversational agent for creating flexible daily automation
Gallo S., Paternò F.
The spread of sensors and intelligent devices of the Internet of things and their integration in daily environments are changing the way we interact with some of the most common objects in everyday life. Therefore, there is an evident need to provide non-expert users with the ability to customize in a simple but effective way the behaviour of these devices based on their preferences and habits. This paper presents RuleBot, a conversational agent that uses machine learning and natural language processing techniques to allow end users to create automation according to a flexible implementation of the trigger-action paradigm, and thereby customize the behaviour of devices and sensors using natural language. In particular, the paper describes the design and implementation ofRuleBot, and reports on a user test and lessons learntSource: AVI 2022 - International Conference on Advanced Visual Interfaces, Frascati, Italy, 06-10/06/2022
DOI: 10.1145/3531073.3531090
Metrics:
Gallo S., Paternò F.
The spread of sensors and intelligent devices of the Internet of things and their integration in daily environments are changing the way we interact with some of the most common objects in everyday life. Therefore, there is an evident need to provide non-expert users with the ability to customize in a simple but effective way the behaviour of these devices based on their preferences and habits. This paper presents RuleBot, a conversational agent that uses machine learning and natural language processing techniques to allow end users to create automation according to a flexible implementation of the trigger-action paradigm, and thereby customize the behaviour of devices and sensors using natural language. In particular, the paper describes the design and implementation ofRuleBot, and reports on a user test and lessons learntSource: AVI 2022 - International Conference on Advanced Visual Interfaces, Frascati, Italy, 06-10/06/2022
DOI: 10.1145/3531073.3531090
Metrics:
See at:
ISTI Repository | dl.acm.org 
| CNR ExploRA
2022
Conference article
Open Access
Towards understanding the transparency of automations in daily environments
Paternò F., Gallo S., Manca M., Mattioli A., Santoro C.
This paper outlines a proposal for how to address transparency of automations in daily environments, such as smart homes, based on experiences carried out in previous projects. The trigger-action programming paradigm has been used to describe and implement such automations in both commercial and research tools. Such automations can be generated through machine learning techniques or directly by the end users or through an interaction between an intelligent agent and the user. When they are executed the resulting behaviour does not always result in the desired actions, and users may have difficulties in understanding and controlling them. Thus, there is a need for design criteria and associated tools that help people to understand and control what happens with the automations active in the environments where they live, and explain how they work and can be modified to better meet their needs.Source: IUI-WS 2022 - Workshops at the International Conference on Intelligent User Interfaces (IUI) 2022, pp. 187–191, Helsinki, Finland, 21-22/03/2022
Paternò F., Gallo S., Manca M., Mattioli A., Santoro C.
This paper outlines a proposal for how to address transparency of automations in daily environments, such as smart homes, based on experiences carried out in previous projects. The trigger-action programming paradigm has been used to describe and implement such automations in both commercial and research tools. Such automations can be generated through machine learning techniques or directly by the end users or through an interaction between an intelligent agent and the user. When they are executed the resulting behaviour does not always result in the desired actions, and users may have difficulties in understanding and controlling them. Thus, there is a need for design criteria and associated tools that help people to understand and control what happens with the automations active in the environments where they live, and explain how they work and can be modified to better meet their needs.Source: IUI-WS 2022 - Workshops at the International Conference on Intelligent User Interfaces (IUI) 2022, pp. 187–191, Helsinki, Finland, 21-22/03/2022
See at:
ceur-ws.org | ISTI Repository | CNR ExploRA