How far can automatic translation engines be used as a tool for stylistic analysis?
| dc.contributor.author | Crosbie, Tess | en_GB |
| dc.contributor.author | French, Tim | en_GB |
| dc.contributor.author | Conrad, Marc | en_GB |
| dc.date.accessioned | 2013-04-07T19:01:25Z | |
| dc.date.available | 2013-04-07T19:01:25Z | |
| dc.date.issued | 2012 | |
| dc.identifier.citation | Crosbie, T., French, T. and Conrad, M. (2012) 'How far can automatic translation engines be used as a tool for stylistic analysis?,' Information Society (i-Society), International Conference on : 503-507 | en_GB |
| dc.identifier.isbn | 9781467308380 | |
| dc.identifier.uri | http://hdl.handle.net/10547/279213 | |
| dc.description.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. | |
| dc.language.iso | en | en |
| dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | en_GB |
| dc.relation.url | https://ieeexplore.ieee.org/document/6285033 | en_GB |
| dc.subject | literary analysis | en_GB |
| dc.subject | machine translation | en_GB |
| dc.title | How far can automatic translation engines be used as a tool for stylistic analysis? | en |
| dc.type | Conference papers, meetings and proceedings | en |
| html.description.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. |