Title :
How far can automatic translation engines be used as a tool for stylistic analysis?
Author :
Crosbie, T. ; French, Tim ; Conrad, Marc
Author_Institution :
Dept. of Comput. Sci. & Technol., Univ. of Bedfordshire, Luton, UK
Abstract :
This pilot study investigates the potential of automatic translation engines to be used as a tool for literary stylistic analysis. By translating from English into one of 62 languages and then re-translating back into English, the resulting texts were compared with a stylistic analysis of the original. Although the similarity index varied widely between languages - between 90% and 32.9% - many stylistic features were retained. However, more subtle features of the texts were lost in the translation process. The similarity index gives a good indication of the literary subtlety / quality of the text, suggesting that this process may be useful as a preliminary “filtering” technique in deeper stylistic studies.
Keywords :
language translation; natural language processing; probability; statistical analysis; text analysis; English; automatic translation engines; filtering technique; literary stylistic analysis; literary subtlety; probabilistic statistical machine techniques; text quality; translation process; Blades; Computers; Context; Earth; Humans; Sun; Terrestrial atmosphere; literary analysis; machine translation;
Conference_Titel :
Information Society (i-Society), 2012 International Conference on
Conference_Location :
London
Print_ISBN :
978-1-4673-0838-0