Efficient Inference and Structured Learning for Semantic Role Labeling
Citations Over TimeTop 1% of 2015 papers
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.
Related Papers
- → Shallow Semantic Parsing Based on FrameNet, VerbNet and PropBank(2006)22 cited
- → A comparative study on generalization of semantic roles in FrameNet(2009)27 cited
- Using Ontologies for Semi-automatic Linking VerbaLex with FrameNet(2010)
- Czech Verbs in FrameNet Semantics(2009)
- → Optimal Telecommunications Network Expansion Using Mixed Linear Integer Programming(2022)