Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Vincent, Sebastian"'
Incorporating extra-textual context such as film metadata into the machine translation (MT) pipeline can enhance translation quality, as indicated by automatic evaluation in recent work. However, the positive impact of such systems in industry remain
Externí odkaz:
http://arxiv.org/abs/2407.00108
Efficient utilisation of both intra- and extra-textual context remains one of the critical gaps between machine and human translation. Existing research has primarily focused on providing individual, well-defined types of context in translation, such
Externí odkaz:
http://arxiv.org/abs/2305.15904
Autor:
Vincent, Sebastian, Dowek, Alice, Sumner, Rowanne, Blundell, Charlotte, Preston, Emily, Bayliss, Chris, Oakley, Chris, Scarton, Carolina
Sensitising language models (LMs) to external context helps them to more effectively capture the speaking patterns of individuals with specific characteristics or in particular environments. This work investigates to what extent rich character and fi
Externí odkaz:
http://arxiv.org/abs/2303.16618
This paper describes the SLT-CDT-UoS group's submission to the first Special Task on Formality Control for Spoken Language Translation, part of the IWSLT 2022 Evaluation Campaign. Our efforts were split between two fronts: data engineering and alteri
Externí odkaz:
http://arxiv.org/abs/2205.05990
Publikováno v:
Proceedings of the 23rd Annual Conference of the European Association for Machine Translation, p. 121-130, Ghent, Belgium, June 2022
Unlike English, morphologically rich languages can reveal characteristics of speakers or their conversational partners, such as gender and number, via pronouns, morphological endings of words and syntax. When translating from English to such language
Externí odkaz:
http://arxiv.org/abs/2205.04747
Autor:
Vincent, Sebastian T.
State-of-the-art (SOTA) neural machine translation (NMT) systems translate texts at sentence level, ignoring context: intra-textual information, like the previous sentence, and extra-textual information, like the gender of the speaker. Because of tha
Externí odkaz:
http://arxiv.org/abs/2102.10979
Autor:
Joseph, Vincent Sebastian, Calais, Theo, Stalin, Thileepan, Jain, Snehal, Thanigaivel, Naresh Kumar, Sanandiya, Naresh D., Valdivia y Alvarado, Pablo
Publikováno v:
In Applied Materials Today March 2021 22
Autor:
Theo Calais, Vincent Sebastian Joseph, Snehal Jain, Thileepan Stalin, Pablo Valdivia Y Alvarado
Publikováno v:
Materials Today: Proceedings. 70:218-223
Autor:
Vincent, Sebastian, Sumner, Rowanne, Dowek, Alice, Blundell, Charlotte, Preston, Emily, Bayliss, Chris, Oakley, Chris, Scarton, Carolina
Personalisation of language models for dialogue sensitises them to better capture the speaking patterns of people of specific characteristics, and/or in specific environments. However, rich character annotations are difficult to come by and to succes
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ac27d6a5f68af13a8c476d42297e1dbd
Autor:
Vincent Sebastian Pande
This study sought to ascertain the different ways in which men contribute to safe motherhood, particularly during pregnancy care. The main question was to what extent men play their roles during pregnancy care? In order to solve this question, the st
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4d8ec3591d1e18395e38a0c37dd2acb6
https://doi.org/10.4018/978-1-6684-6299-7.ch025
https://doi.org/10.4018/978-1-6684-6299-7.ch025