Efficient Inference and Structured Learning for Semantic Role Labeling

Oscar Täckström, Kuzman Ganchev, Dipanjan Das


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.
Anthology ID:
Q15-1003
Volume:
Transactions of the Association for Computational Linguistics, Volume 3
Month:
Year:
2015
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
29–41
Language:
URL:
https://aclanthology.org/Q15-1003
DOI:
10.1162/tacl_a_00120
Bibkey:
Cite (ACL):
Oscar Täckström, Kuzman Ganchev, and Dipanjan Das. 2015. Efficient Inference and Structured Learning for Semantic Role Labeling. Transactions of the Association for Computational Linguistics, 3:29–41.
Cite (Informal):
Efficient Inference and Structured Learning for Semantic Role Labeling (Täckström et al., TACL 2015)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/Q15-1003.pdf
Data
FrameNet