Today, access to the Internet provides access to various forms of knowledge like free online lecture series offered by prestigious universities, massive open online courses, films and books, and Wikipedia. In addition, it is possible to join online communities on any topic of interest, get to know people with common interests, exchange thoughts and participate in debates. To enable access to these unprecedented knowledge bases, it is crucial to be able to translate texts into any language known by users. For this reason, Machine Translation has been a very active research field for the last thirty years. In this paper, we investigate the task of Chinese-Italian translations by exploiting Neural Machine Translation approaches. We trained several deep neural networks starting from two already available datasets containing Chinese-Italian parallel corpora. Then, we compared their performance against some of the most common machine translation services freely available online. In particular, we take advantage of Microsoft Translator, Google Translate, DeepL, and ModernMT.

Delnevo G., Im M., Tse R., Lam C.-T., Tang S.-K., Salomoni P., et al. (2023). Italian-Chinese Neural Machine Translation: results and lessons learnt. New York : Association for Computing Machinery [10.1145/3582515.3609567].

Italian-Chinese Neural Machine Translation: results and lessons learnt

Delnevo G.;Salomoni P.;Pau G.;Ghini V.;Mirri S.
2023

Abstract

Today, access to the Internet provides access to various forms of knowledge like free online lecture series offered by prestigious universities, massive open online courses, films and books, and Wikipedia. In addition, it is possible to join online communities on any topic of interest, get to know people with common interests, exchange thoughts and participate in debates. To enable access to these unprecedented knowledge bases, it is crucial to be able to translate texts into any language known by users. For this reason, Machine Translation has been a very active research field for the last thirty years. In this paper, we investigate the task of Chinese-Italian translations by exploiting Neural Machine Translation approaches. We trained several deep neural networks starting from two already available datasets containing Chinese-Italian parallel corpora. Then, we compared their performance against some of the most common machine translation services freely available online. In particular, we take advantage of Microsoft Translator, Google Translate, DeepL, and ModernMT.
2023
Proceedings of the 2023 ACM Conference on Information Technology for Social Good
455
461
Delnevo G., Im M., Tse R., Lam C.-T., Tang S.-K., Salomoni P., et al. (2023). Italian-Chinese Neural Machine Translation: results and lessons learnt. New York : Association for Computing Machinery [10.1145/3582515.3609567].
Delnevo G.; Im M.; Tse R.; Lam C.-T.; Tang S.-K.; Salomoni P.; Pau G.; Ghini V.; Mirri S.
File in questo prodotto:
File Dimensione Formato  
nmt-post-print.pdf

accesso aperto

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 232.91 kB
Formato Adobe PDF
232.91 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/953675
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact