Articles producció científica> Filologies Romàniques

Who has the last word? Lessons from using ChatGPT to develop an AI-based Spanish writing assistant

  • Identification data

    Identifier: imarina:9364597
    Authors:
    Sven TarpAntoni Nomdedeu Rull
    Abstract:
    This article deals with the complex relationship between human intelligence and so-called artificial intelligence in the context of an ongoing project to develop a writing assistant for Spanish learners, both native and non-native. The authors have used ChatGPT to generate validation data to assess the performance of the language model on different parameters before testing it with real users. The article describes how they approached the generation of validation data, what they learned along the way, and what the results were. It first introduces the project and describes its main phases. It then explains the criteria the authors used to determine the types of problems to be covered by the validation data, and how they instructed the chatbot to generate this data. Finally, it summarises the main lessons they learnt from working with the chatbot and some of the challenges they faced in getting it to work properly. The description is accompanied by numerous examples. By engaging with the chatbot in a critical and constructive way, and by establishing close interdisciplinary collaboration with IT specialists, the authors conclude that the key challenge is to demonstrate in practice that humans, not the chatbot, are the masters. In this context, they argue that generative AI language models are not here to replace us, but to help us produce faster and with higher quality to meet our growing and increasingly diverse demands for a better life.
  • Others:

    Author, as appears in the article.: Sven Tarp; Antoni Nomdedeu Rull
    Department: Filologies Romàniques
    URV's Author/s: Nomdedeu Rull, Antonio
    Abstract: This article deals with the complex relationship between human intelligence and so-called artificial intelligence in the context of an ongoing project to develop a writing assistant for Spanish learners, both native and non-native. The authors have used ChatGPT to generate validation data to assess the performance of the language model on different parameters before testing it with real users. The article describes how they approached the generation of validation data, what they learned along the way, and what the results were. It first introduces the project and describes its main phases. It then explains the criteria the authors used to determine the types of problems to be covered by the validation data, and how they instructed the chatbot to generate this data. Finally, it summarises the main lessons they learnt from working with the chatbot and some of the challenges they faced in getting it to work properly. The description is accompanied by numerous examples. By engaging with the chatbot in a critical and constructive way, and by establishing close interdisciplinary collaboration with IT specialists, the authors conclude that the key challenge is to demonstrate in practice that humans, not the chatbot, are the masters. In this context, they argue that generative AI language models are not here to replace us, but to help us produce faster and with higher quality to meet our growing and increasingly diverse demands for a better life.
    Thematic Areas: Ciencias humanas Ciencias sociales Comunicación Filologia, lingüística i sociolingüística Filologías Language & linguistics Language and linguistics Letras / linguística Lingüística Lingüística general y aplicada Linguistics Linguistics and language
    licence for use: https://creativecommons.org/licenses/by/3.0/es/
    Author's mail: antonio.nomdedeu@urv.cat
    Author identifier: 0000-0003-2447-6954
    Record's date: 2024-07-27
    Papper version: info:eu-repo/semantics/publishedVersion
    Link to the original source: https://revistas.ucm.es/index.php/CLAC/article/view/91985
    Papper original source: Circulo De Linguistica Aplicada A La Comunicacion. (97): 309-321
    APA: Sven Tarp; Antoni Nomdedeu Rull (2024). Who has the last word? Lessons from using ChatGPT to develop an AI-based Spanish writing assistant. Circulo De Linguistica Aplicada A La Comunicacion, (97), 309-321
    Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
    Article's DOI: 10.5209/clac.91985
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2024
    Publication Type: Journal Publications
  • Keywords:

    Language & Linguistics,Language and Linguistics,Linguistics,Linguistics and Language
    Ciencias humanas
    Ciencias sociales
    Comunicación
    Filologia, lingüística i sociolingüística
    Filologías
    Language & linguistics
    Language and linguistics
    Letras / linguística
    Lingüística
    Lingüística general y aplicada
    Linguistics
    Linguistics and language
  • Documents:

  • Cerca a google

    Search to google scholar