|
Informatics Report Series
|
|
|
|
|
|
|
|
|
| Title:Data-defined kernels for parse reranking derived from probabilistic models |
| Authors:
James Henderson
; Ivan Titov
|
| Date: 2005 |
| Publication Title:Proc. 43nd Meeting of Association for Computational Linguistics (ACL 2005) |
| Publisher:Association for Computational Linguistics |
|
Publication Type:Conference Paper
Publication Status:Published
|
|
Page Nos:181-188
|
|
DOI:10.3115/1219840.1219863
|
- Abstract:
-
Previous research applying kernel methods to natural language parsing have focussed on proposing kernels over parse trees, which are hand-crafted based on domain knowledge and computational considerations. In this paper we propose a method for defining the kernel in terms of a probabilistic model of parsing. This model is then trained, so that the parameters of the probabilistic model reflect the generalizations in the training data. The method we propose then uses these trained parameters to define a kernel for reranking parse trees. In experiments, we use a neural network based statistical parser as the probabilistic model, and use the resulting kernel with the Voted Perceptron algorithm to rerank the top 20 parses from the probabilistic model. This method achieves a significant improvement over the accuracy of the probabilistic model alone.
- Links To Paper
- 1st Link
- Bibtex format
- @InProceedings{EDI-INF-RR-1014,
- author = {
James Henderson
and Ivan Titov
},
- title = {Data-defined kernels for parse reranking derived from probabilistic models},
- book title = {Proc. 43nd Meeting of Association for Computational Linguistics (ACL 2005)},
- publisher = {Association for Computational Linguistics},
- year = 2005,
- pages = {181-188},
- doi = {10.3115/1219840.1219863},
- url = {http://homepages.inf.ed.ac.uk/jhender6/papers/henderson_acl05.pdf},
- }
|
