Year: 2015
Type: article
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.
DOI: 10.1162/tacl_a_00120
Authors: Oscar Täckström, Kuzman Ganchev, Dipanjan Das
Institution: Google (United States)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W2114590102