Learning in natural language: theory and algorithmic approaches
ConLL '00 Proceedings of the 2nd workshop on Learning language in logic and the 4th conference on Computational natural language learning - Volume 7
Hi-index | 0.00 |
We study memory-based learning methods and show that they can be viewed as learning linear predictors over commonly used feature spaces. We suggest that this view allows one to study memory based methods and other successful learning algorithms used in NLP within the same computational framework and may result in improved algorithms and a better understanding for the role of learning in natural language inferences.