Structure learning for natural language processing
Saunders, C.J., Szedmak, S. and Niranjan, M. (2009) Structure learning for natural language processing. Proceedings of the 2009 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2009), 6 pp.-.
Download
Full text not available from this repository.
Description/Abstract
We applied a structure learning model, Max-Margin Structure (MMS), to natural language processing (NLP) tasks, where the aim is to capture the latent relationships within the output language domain. We formulate this model as an extension of multi-class Support Vector Machine (SVM) and present a perceptron-based learning approach to solve the problem. Experiments are carried out on two related NLP tasks: part-of-speech (POS) tagging and machine translation (MT), illustrating the effectiveness of the model.
| Item Type: | Article |
|---|---|
| Additional Information: | Imported from ISI Web of Science |
| Divisions: | Faculty of Physical and Applied Science > Electronics and Computer Science > Comms, Signal Processing & Control |
| Item ID: | 270324 |
| Date Deposited: | 21 Apr 2010 07:46 |
| Last Modified: | 02 Mar 2012 12:42 |
| Contributors: | Saunders, C.J. (Author) Szedmak, S. (Author) Niranjan, M. (Author) |
| Date: | 2009 |
| Additional Information: | Imported from ISI Web of Science |
| Status: | Unpublished |
| Further Information: | Google Scholar |
| ISI Citation Count: | 0 |
| URI: | http://eprints.soton.ac.uk/id/eprint/270324 |
Actions (login required)
 |
View Item |
