A Spanish Corpus for Talking to the Elderly

Justo, Raquel; Letaifa, Leila Ben; Olaso, Javier Mikel; López-Zorrilla, Asier; Velasco, Mikel de; Vázquez, Alain García; Torres, M. Inés

doi:10.1007/978-981-15-8395-7_13

Cited by 3 publications

(9 citation statements)

References 20 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The nutrition scenario is the coaching session, based on the GROW model presented in Section 3.2 . Both dialogues were designed based on two references: the documents provided by the professional coach mentioned in Section 3 and a corpus of dialogues between elderly people and a simulated VC acquired through a Wizard of Oz technique [ 71 ].…”

Section: Dialogue Management To Perform Coaching Strategiesmentioning

confidence: 99%

Dialogue Management and Language Generation for a Robust Conversational Virtual Coach: Validation and User Study

Vázquez

Zorrilla

Olaso

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Designing human–machine interactive systems requires cooperation between different disciplines is required. In this work, we present a Dialogue Manager and a Language Generator that are the core modules of a Voice-based Spoken Dialogue System (SDS) capable of carrying out challenging, long and complex coaching conversations. We also develop an efficient integration procedure of the whole system that will act as an intelligent and robust Virtual Coach. The coaching task significantly differs from the classical applications of SDSs, resulting in a much higher degree of complexity and difficulty. The Virtual Coach has been successfully tested and validated in a user study with independent elderly, in three different countries with three different languages and cultures: Spain, France and Norway.

show abstract

Section: Dialogue Management To Perform Coaching Strategiesmentioning

confidence: 99%

Dialogue Management and Language Generation for a Robust Conversational Virtual Coach: Validation and User Study

Vázquez

Zorrilla

Olaso

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the 80’s, chatbots have been mainly developed for the gaming industry and they have been used for testing if individuals can recognize them as being machines or humans ( Bächle et al, 2018 ). Although early chatbots lacked the ability to maintain a conversation going ( Hussain et al, 2019 ), as the conversational agents use more and more natural language processing, they pass the Turing Test ( Justo et al, 2021 ). In 1995, ALICE chatbot, a highly awarded software, has been developed and has been considered the “most human computer” until that moment ( Adamopoulou and Moussiades, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

“…The drawback of a task-oriented system is that it cannot exceed the programmed topic scope ( Su et al, 2017 ). Non-task-oriented chatbots is rather keen on conversating for entertainment purpose in all kinds of domains and in an unstructured manner ( Hussain et al, 2019 ; Justo et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

“…The functionality of chatbots is either for entertainment or utilitarian ( Zamora, 2017 ). Conversational systems are increasingly used and are useful both at home and for leisure (e.g., Alexa, Siri), or in our professional life (e.g., Siri, Cortana) for managing the schedule or for educational purposes ( Justo et al, 2021 ; Valtolina and Hu, 2021 ). Chatbots are mainly used for obtaining information, for interacting needs and out of curiosity ( Gunathilaka et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

“…Although AI developments in assistive technology are advanced, there is still work to be done for achieving a proper chatbot for end aging users ( De Arriba-Pérez et al, 2021 ). Thus, the existing studies refer to presenting, designing, and testing prototypes of conversational agents with meaningful, empathetic emotional, and friendship capabilities ( Yang et al, 2015 ; Bassi et al, 2021 ), with personalized entertainment content access ( De Arriba-Pérez et al, 2021 ), with workplace environment facilities ( Bächle et al, 2018 ), with capabilities to promote healthy habits through a coaching model ( Justo et al, 2021 ), with public administration abilities ( Miliani et al, 2021 ), with virtual caregiving attributions ( Su et al, 2017 ; Ryu et al, 2020 ; Valtolina and Hu, 2021 ; Miura et al, 2022 ).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Interacting with chatbots later in life: A technology acceptance perspective in COVID-19 pandemic situation

Iancu

2023

Front. Psychol.

View full text Add to dashboard Cite

IntroductionWithin the technological development path, chatbots are considered an important tool for economic and social entities to become more efficient and to develop customer-centric experiences that mimic human behavior. Although artificial intelligence is increasingly used, there is a lack of empirical studies that aim to understand consumers’ experience with chatbots. Moreover, in a context characterized by constant population aging and an increased life-expectancy, the way aging adults perceive technology becomes of great interest. However, based on the digital divide (unequal access to technology, knowledge, and resources), and since young adults (aged between 18 and 34 years old) are considered to have greater affinity for technology, most of the research is dedicated to their perception. The present paper investigates the way chatbots are perceived by middle-aged and aging adults in Romania.MethodsAn online opinion survey has been conducted. The age-range of the subjects is 40–78 years old, a convenience sampling technique being used (N = 235). The timeframe of the study is May–June 2021. Thus, the COVID-19 pandemic is the core context of the research. A covariance-based structural equation modelling (CB-SEM) has been used to test the theoretical assumptions as it is a procedure used for complex conceptual models and theory testing.ResultsThe results show that while perceived ease of use is explained by the effort, the competence, and the perceive external control in interacting with chatbots, perceived usefulness is supported by the perceived ease of use and subjective norms. Furthermore, individuals are likely to further use chatbots (behavioral intention) if they consider this interaction useful and if the others’ opinion is in favor of using it. Gender and age seem to have no effect on behavioral intention. As studies on chatbots and aging adults are few and are mainly investigating reactions in the healthcare domain, this research is one of the first attempts to better understand the way chatbots in a not domain-specific context are perceived later in life. Likewise, judging from a business perspective, the results can help economic and social organizations to improve and adapt AI-based interaction for the aging customers.

show abstract

A Multilingual Neural Coaching Model with Enhanced Long-term Dialogue Structure

Zorrilla

Torres

2022

ACM Trans. Interact. Intell. Syst.

Self Cite

View full text Add to dashboard Cite

In this work we develop a fully data driven conversational agent capable of carrying out motivational coaching sessions in Spanish, French, Norwegian and English. Unlike the majority of coaching, and in general, well-being related conversational agents that can be found in the literature, ours is not designed by hand-crafted rules. Instead, we directly model the coaching strategy of professionals with end users. To this end, we gather a set of virtual coaching sessions through a Wizard of Oz platform, and apply state of the art Natural Language Processing techniques. We employ a transfer learning approach, pretraining GPT2 neural language models and fine-tuning them on our corpus. However, since these only take as input a local dialogue history, a simple fine-tuning procedure is not capable of modeling the long-term dialogue strategies that appear in coaching sessions. To alleviate this issue, we first propose to learn dialogue phase and scenario embeddings in the fine-tuning stage. These indicate to the model at which part of the dialogue it is and which kind of coaching session it is carrying out. Second, we develop global deep learning system which controls the long-term structure of the dialogue. We also show that this global module can be used to visualize and interpret the decisions taken by the the conversational agent, and that the learnt representations are comparable to dialogue acts. Automatic and human evaluation show that our proposals serve to improve the baseline models. Finally, interaction experiments with coaching experts indicate that system is usable and gives raise to positive emotions in Spanish, French and English, while the results in Norwegian point out that there is still work to be done in fully data driven approaches with very low resource languages.

show abstract

A Spanish Corpus for Talking to the Elderly

Cited by 3 publications

References 20 publications

Dialogue Management and Language Generation for a Robust Conversational Virtual Coach: Validation and User Study

Dialogue Management and Language Generation for a Robust Conversational Virtual Coach: Validation and User Study

Interacting with chatbots later in life: A technology acceptance perspective in COVID-19 pandemic situation

A Multilingual Neural Coaching Model with Enhanced Long-term Dialogue Structure

Contact Info

Product

Resources

About