An Analysis of Neural Machine Translation on Cross-Cultural Communication: A Case Study of Airbnb's Translation Function
Öz
This study examines the theoretical and practical implications of the online platform Airbnb's automatic translation function, which enables cross-cultural communication without users needing to know each other’s language. Users are unaware of the language used during the communication between parties on this application and website, thus making it seamless to communicate without speaking the same language. The research encompasses an in-depth analysis of the neural machine translation (NMT) models powering Airbnb's translation function, exploring their capabilities and limitations. Methodologically, the study has employed a content analysis of the website’s language and translation policies as well as a combination of case studies to evaluate the user experience and linguistic accuracy of the translations. The findings of this study highlight both the strengths and areas for improvement in current translation technologies, offering insights into how they can be refined to serve global platforms better. This research has also revealed a common use of automatic translation and provides practical recommendations for enhancing the quality and user experience. By bridging theoretical frameworks with practical applications, this study aims to discuss future developments in translation technologies and their integration into everyday communication tools. The originality of this work lies in exposing the use of automatic translation and the impact of such technologies on user interactions. The significance of this study is underscored by its potential to enhance our understanding of how automated translations can bridge linguistic and cultural gaps in global communication and explain the inner workings of such automatic translation mechanisms.
Anahtar Kelimeler
Airbnb, automatic translation, cross-cultural communication, neural machine translation, translation technologies
Kaynakça
- Airbnb Newsroom (2021). “Translation engine launches reviews after expanding to messages this summer”. Retrieved from https://news.airbnb.com/translation-engine-launches-reviewsafter-expanding-to-messages-this-summer/.
- Academia.edu (n.d.). “Translating cultural nuances: Challenges and strategies”. Retrieved from https://www.academia.edu/107842485/Translating_Cultural_Nuances_Challenges_and_Strategies.
- Bal, Dilara & Demirel Fakiroğlu, Gözde. (2023). Orthographic Errors in English Abstracts Written by Turkish Researchers. Dilbilim(40), 89-96.
- Brown, Tom B. et al. (2020). “Language models are few-shot learners”, Advances in Neural Information Processing Systems, 33, 1877–1901.
- Castilho, Sheila et al. (2018). “Integrating neural machine translation into translation workflows”, Machine Translation, 32(4), 275–298.
- DeepAI. (n.d.). “Neural machine translation”. Retrieved from [https://deepai.org/machine-learningmodel/neural-machine-translation]
- Gutiérrez, Javier et al. (2017). “The eruption of Airbnb in tourist cities: Comparing spatial patterns of hotels and peer-to-peer accommodation in Barcelona”, Tourism Management, 62, 278–291.
- Guttentag, Daniel (2019). “Airbnb: Disruptive innovation and the rise of an informal tourism accommodation sector”, Current Issues in Tourism, 22(9), 1011–1035.
- iTranslate. (n.d.). “An introduction to the architecture of neural machine translation”. Retrieved from https://itranslate.com/blog/an-introduction-to-the-architecture-of-neural-machinetranslation
- Jiménez-Crespo, Miguel Ángel (2017). Crowdsourcing and online collaborative translations: Expanding the limits of translation studies. Amsterdam: John Benjamins Publishing.
