Academic Paper |
|
|
|
|
| Title: | Segmenting documents by stylistic character |
| Author: | Neil Graham |
| Institution: | University of Toronto |
| Author: | Graeme Hirst |
| Email: | click here to access email |
| Homepage: | http://www.cs.utoronto.ca/~gh/ |
| Institution: | University of Toronto |
| Author: | Bhaskara Marthi |
| Institution: | University of Toronto |
| Linguistic Field: | Computational Linguistics |
| Abstract: | As part of a larger project to develop an aid for writers that would help to eliminate stylistic inconsistencies within a document, we experimented with neural networks to find the points in a text at which its stylistic character changes. Our best results, well above baseline, were achieved with time-delay networks that used features related to the author's syntactic preferences, whereas low-level and vocabulary-based features were not found to be useful. An alternative approach with character bigrams was not successful. |
|
|
|
|
This article appears in Natural Language Engineering Vol. 11, Issue 4, which you can read on Cambridge's site or on LINGUIST . |
|
|
|
|
Back
Add a new paper Return to Academic Papers main page Return to Directory of Linguists main page |
|


