Incremental integer linear programming for non-projective dependency parsing

Incremental integer linear programming for non-projective dependency parsing (2006)

by Sebastian Riedel , James Clarke

Venue:	In EMNLP
Citations:	30 - 3 self

Datum	Value	Source
TITLE	Incremental integer linear programming for non-projective dependency parsing	INFERENCE
AUTHOR NAME	Sebastian Riedel	SVM HeaderParse 0.2
AUTHOR AFFIL	School of Informatics, University of Edinburgh	SVM HeaderParse 0.2
AUTHOR ADDR	2 Bucclecuch Place, Edinburgh EH8 9LW, UK	SVM HeaderParse 0.2
AUTHOR NAME	James Clarke	SVM HeaderParse 0.2
AUTHOR AFFIL	School of Informatics, University of Edinburgh	SVM HeaderParse 0.2
AUTHOR ADDR	2 Bucclecuch Place, Edinburgh EH8 9LW, UK	SVM HeaderParse 0.2
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	SVM HeaderParse 0.2
YEAR	2006	INFERENCE
VENUE	In EMNLP	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	129--137	INFERENCE
CITATIONS	16 found	ParsCit 1.0