Gemini Advanced e ChatGPT 4o: sfide nella traduzione di un film di animazione dal portoghese brasiliano

Carla Valeria de Souza Faria

doi:10.13125/rhesis/6513

Carla Valeria de Souza Faria Università degli Studi di Trieste

DOI: https://doi.org/10.13125/rhesis/6513

Keywords: Artificial intelligence, Gemini Advanced, ChatGPT 4o, animation film translation, contrastive analysis

Abstract

This paper aims to analyze the ability of Gemini Advanced and ChatGPT 4o to translate an animated film for children from Brazilian Portuguese into Italian, taking into account the target audience (children) and a language as close as possible to spontaneous Italian speech. The translations were also compared with those of students, mostly Italian speakers, of Portuguese as a foreign language at B1/B2 CEFR levels. The results show that although the two systems were able to produce good translations, they still produced incorrect, inaccurate or context-inappropriate translations requiring human intervention. Furthermore, the preliminary results of this research may serve as a guide for the teaching of Portuguese as a foreign language and pragmatic-discursive aspects in audiovisual translation from a contrastive perspective.

Downloads

Download data is not yet available.

References

Aulete digital, Dicionário online Caldas Aulete, Lexikon editora digital <https://aulete.com.br/> (consultato il 20/10/2024).

Bechara, Evanildo (2009), Moderna Gramática Portuguesa, 37a ed. rev. ampl. e atual. conforme o novo Acordo Ortográfico, Rio de Janeiro, Nova Fronteira.

Bertuccelli Papi, Marcella (2010), ‘Convenevoli’, in Treccani Enciclopedia dell’Italiano, (consultato il 02/12/2024).

Caligiore, Daniele (2022), IA istruzioni per l’uso. Capire l’Intelligenza Artificiale per gestirne opportunità e rischi, Bologna, il Mulino, edizione e-book.

Canobbio, Sabina (2011), ‘Saluto, formule di’, in Treccani Enciclopedia dell’Italiano (consultato il 02/12/2024).

Cunha, Celso; Cintra, Lindley (1985), Nova Gramática do Português Contemporâneo, Rio de Janeiro, Nova Fronteira.

DeepL Team (a cura di), ‘Ti presentiamo Deepl Voice, l’interprete per ogni occasione’, DeepL Blog, <https://www.deepl.com/it/blog/deepl-voice> (consultato il 23/12/2024).

Dwivedi, Yogesh K.; Kshetri, Nir; Hughes, Laurie; Slade, Emma Louise; Jeyaraj, Anand; Kumar Kar, Arpan; Baabdullah, Abdullah M.; Koohang, Alex; Raghavan, Vishnupriya; Ahuja, Manju; Albanna, Hanaa; Albashrawi, Mousa Ahmad; Al-Busaidi, Adil S.; Balakrishna, Janarthanan; Barlette, Yves; Basu, Sriparna; Indranil, Bose; Brooks, Laurence; Buhalis, Dimitrios; Carter, Lemuria; Wright, Ryan (2023), ‘So what if ChatGPT wrote it? Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI research, practice and policy’, International Journal of Information Management 71, <https://doi.org/10.1016/j.ijinfomgt.2023.102642>, 1-63.

Fiorentini, Ilaria (2024), ‘L’italiano dei giovani’, in Ballarè, Silvia; Fiorentini, Ilaria; Miola, Emanuele (a cura di), Le varietà dell’italiano contemporaneo, Roma, Carocci, 99-113.

Gigerenzer, Gerd (2022), How to Stay Smart in a Smart World. Why Human Intelligence Still Beats Algorithms, London, The MIT Press.

Google, Gemini Advanced, <https://gemini.google.com/Advanced?hl=it> (consultato il 03/08/2024).

Lubello, Sergio (2019), ‘Morfologia e Sintassi’, in Librandi, Rita (a cura di), L’italiano: strutture, usi, varietà, Roma, Carocci, 71-133.

Manzotti, Riccardo; Rossi, Simone (2023), Io & Ia. Mente, Cervello e GPT, Soveria Mannelli, Rubbettino.

Mariani, Marcello (2023), ‘AI platforms, ChatGPT, and Innovation’, in Dwivedi, Yogesh K.; Kshetri, Nir; Hughes, Laurie; Slade, Emma Louise; Jeyaraj, Anand; Kumar Kar, Arpan; Baabdullah, Abdullah M.; Koohang, Alex; Raghavan, Vishnupriya; Ahuja, Manju; Albanna, Hanaa; Albashrawi, Mousa Ahmad; Al-Busaidi, Adil S.; Balakrishna, Janarthanan; Barlette, Yves; Basu, Sriparna; Indranil, Bose; Brooks, Laurence; Buhalis, Dimitrios; Carter, Lemuria; Wright, Ryan (2023), ‘So what if ChatGPT wrote it? Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI research, practice and policy’, International Journal of Information Management, 71 (2023), 5-6. <https://doi.org/10.1016/j.ijinfomgt.2023.102642>.

Munhoz, Paulo (dir.) (2012), Brichos - a floresta é nossa, Brasil, Tecnokena Audiovisual e Multimídia Ltda, <https://youtu.be/wmqsmSJWHe0?si=n9Rp-X4XaGz6iXAk> (consultato il 23/02/2025).

Oliveira, Fátima (2013), ‘Tempo verbal’, in Raposo, Eduardo B. P. et al. (orgs.), Gramática do português, vol. I, Lisboa, Fundação Calouste Gulbenkian, 509-553.

OpenAI (2024), Hello GPT-4o, May 2024, <https://openai.com/index/hello-gpt-4o/> (consultato il 03/08/2024).

Pappas, Illias O. (2023), ‘ChatGPT for Human Augmentation’, in Dwivedi, Yogesh K.; Kshetri, Nir; Hughes, Laurie; Slade, Emma Louise; Jeyaraj, Anand; Kumar Kar, Arpan; Baabdullah, Abdullah M.; Koohang, Alex; Raghavan, Vishnupriya; Ahuja, Manju; Albanna, Hanaa; Albashrawi, Mousa Ahmad; Al-Busaidi, Adil S.; Balakrishna, Janarthanan; Barlette, Yves; Basu, Sriparna; Indranil, Bose; Brooks, Laurence; Buhalis, Dimitrios; Carter, Lemuria; Wright, Ryan (2023), ‘So what if ChatGPT wrote it? Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI research, practice and policy’, International Journal of Information Management 71 (2023), 9-10. <https://doi.org/10.1016/j.ijinfomgt.2023.102642>.

Quarta, Alessandra; Smorto, Guido (2020), Diritto privato dei mercati globali, Firenze, Le Monnier Università.

Raposo, Eduardo B. P.: Nascimento, Maria Fernanda B. do; Mota, Maria Antónia C. da; Segura, Luísa; Mendes, Amália (2013) (orgs.), Gramática do português, vol. I, Lisboa, Fundação Calouste Gulbenkian.

Rocco, Gabriella (2024), ‘Il progetto di Translated e Cineca per creare il modello di traduzione più avanzato al mondo’, Repubblica, 12/11/2024, <https://www.repubblica.it/tecnologia/2024/11/12/news/translated_cineca_modello_linguistico_traduzioni_leonardo-423613005/> (consultato il 23/12/2024).

SketchEngine, .

Translated, ‘Chi siamo’ <https://translated.com/chi-siamo> (consultato il 23/12/2024).

Telve, Stefano (2019), ‘Testo’, in Librandi, Rita (a cura di), L’italiano: strutture, usi, varietà, Roma, Carocci, 135-182.

UNESCO (2023), Guidance for generative AI in education and research, Paris, Unesco. <https://unesdoc.unesco.org/ark:/48223/pf0000386693> (consultato il 30/07/2024).

UNESCO/IESALC (2023a), ChatGPT and Artificial Intelligence in higher education, Quick start guide, Paris/Caracas, UNESCO/IESALC. <https://unesdoc.unesco.org/ark:/48223/pf0000385146> (consultato il 30/07/2024).

UNESCO/IESALC (2023b), Harnessing the era of artificial intelligence in higher education: A primer for higher education stakeholders, Paris/Caracas, UNESCO/IESALC. <https://unesdoc.unesco.org/ark:/48223/pf0000386670> (consultato il 30/07/2024).

Vaswani, Ashish; Shazeer, Noam; Parmar, Niki; Uszkoreit, Jakob; Jones, Llion; Gomez, Aidan N.; Kaiser, Lukasz; Polosukhin, Illia (2017), Attention Is All You Need, arXiv, 1706.03762v5.

Zanettin, Andrea (2024), ‘Google sfida OpenAi sulle IA in grado di “ragionare”: ecco Gemini Thinking Experimental’, Everyeye.it, 19/12/2024, <https://tech.everyeye.it/notizie/google-sfida-openai-ia-grado-ragionare-gemini-thinking-experimental-765995.html> (consultato il 23/12/2024).

Zanettin, Andrea (2024), ‘OpenAI spiazza tutti e annuncia l’IA o3: il nuovo modello si avvicina all’AGI’, Everyeye.it, 20/12/2024, <https://tech.everyeye.it/notizie/openai-spiazza-annuncia-ia-o3-modello-avvicina-agi-766249.html> (consultato il 23/12/2024).