Efficient Inference and Structured Learning for Semantic Role Labeling
Venue
Transactions of the Association for Computational Linguistics, vol. 3 (2015), pp. 29-41
Publication Year
2015
Authors
Oscar Täckström, Kuzman Ganchev, Dipanjan Das
BibTeX
Abstract
We present a dynamic programming algorithm for efficient constrained inference in
semantic role labeling. The algorithm tractably captures a majority of the
structural constraints examined by prior work in this area, which has resorted to
either approximate methods or off-the-shelf integer linear programming solvers. In
addition, it allows training a globally-normalized log-linear model with respect to
constrained conditional likelihood. We show that the dynamic program is several
times faster than an off-the-shelf integer linear programming solver, while
reaching the same solution. Furthermore, we show that our structured model results
in significant improvements over its local counterpart, achieving state-of-the-art
results on both PropBank- and FrameNet-annotated corpora.
