DMCA
Incremental integer linear programming for non-projective dependency parsing (2006)
Cached
Download Links
| Venue: | In EMNLP |
| Citations: | 63 - 6 self |
BibTeX
@INPROCEEDINGS{Riedel06incrementalinteger,
author = {Sebastian Riedel and James Clarke},
title = {Incremental integer linear programming for non-projective dependency parsing},
booktitle = {In EMNLP},
year = {2006},
pages = {129--137}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Integer Linear Programming has recently been used for decoding in a number of probabilistic models in order to enforce global constraints. However, in certain applications, such as non-projective dependency parsing and machine translation, the complete formulation of the decoding problem as an integer linear program renders solving intractable. We present an approach which solves the problem incrementally, thus we avoid creating intractable integer linear programs. This approach is applied to Dutch dependency parsing and we show how the addition of linguistically motivated constraints can yield a significant improvement over stateof-the-art. 1
Keyphrases
incremental integer non-projective dependency machine translation decoding problem probabilistic model significant improvement integer linear program render integer linear programming complete formulation global constraint certain application intractable integer linear program non-projective dependency parsing
