User Tools
Sidebar
An Introduction to Neural Machine Translation and its Potential for Literary Texts
Neural Machine Translation (NMT), a paradigm to statistical MT introduced only very recently, has already become the state-of-the-art in the field. This talk will provide an introduction to NMT, highlighting the features that make this paradigm so promising. In the second part of the talk I will discuss the potential of NMT for literary text, novels specifically. This is motivated by two claims made about NMT; (i) that it results in more natural translations than previous and can find cultural equivalents better than previous MT approaches, and (ii) that it has an edge on lexically rich texts.
Related papers:
NMT: Víctor M. Sánchez-Cartagena and Antonio Toral. Abu-MaTran at WMT 2016 Translation Task: Deep Learning, Morphological Segmentation and Tuning on Character Sequences. In Proceedings of the 1st Conference on Machine Translation (WMT16). www.statmt.org/wmt16/pdf/W16-2322.pdf
MT on novels: Antonio Toral and Andy Way. Machine-Assisted Translation of Literary Text: A Case Study. In Translation Spaces Vol. 4:2, 2015, pp. 241–268. John Benjamins. ISSN 2211-3711. http://www.computing.dcu.ie/~atoral/publications/2015_translation-spaces_mt-literary-text.pdf
