Efficient Inference and Structured Learning for Semantic Role Labeling

By Oscar Täckström, Kuzman Ganchev, Dipanjan Das. 2015

92 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

End-to-end learning of semantic role labeling using recurrent neural networks (2015, background): “With dynamic programming, (Täckström et al., 2015) enhance the inference efficiency further.”
Deep Semantic Role Labeling: What Works and What’s Next (2017, background): “, 2008) or dynamic programs (Täckström et al., 2015).”
Linguistically-Informed Self-Attention for Semantic Role Labeling (2018, methodology): “…Pun-yakanok et al., 2008), recently deep neural network architectures have surpassed syntactically-informed models (Zhou and Xu, 2015; Marcheg-giani et al., 2017; He et al., 2017; Tan et al., 2018; He et al., 2018), achieving state-of-the art SRL performance with no explicit modeling of syntax.”
Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs (2016, background): “, 2015), systems which perform optimal decoding (Täckström et al., 2015), or of systems that exploit additional, differently-annotated datasets (FitzGerald et al.”
Syntactic Scaffolds for Semantic Structures (2018, methodology): “, 2014) • distance (in tokens) of the span from the target (Täckström et al., 2015) • position of the span with respect to the target (before, after, overlap) (Täckström et al.”
Semantic Role Labeling with Neural Network Factors (2015, methodology): “In addition to comparing to Täckström et al. (2015), whose setup is closest to ours, we also compare to prior state-of-the-art systems from the literature.”
Recent Trends in Deep Learning Based Natural Language Processing [Review Article] (2018, background): “[142] scored a constituent span and its possible role to that predicate with a series of features based on the parse tree.”
End-to-End Learning for Structured Prediction Energy Networks (2017, methodology): “Our data processing and hyperparam-eters are designed to replicate the setup of Wang et al. (2016), who demonstrate state-of-the art results for energy-minimization-based denoising on the dataset.”
A Joint Sequential and Relational Model for Frame-Semantic Parsing (2017, methodology): “) is a graphical model with global factors (Täckström et al., 2015); FitzGerald (Struct.”
A Sequence-to-Sequence Model for Semantic Role Labeling (2018, unknown): “214 (Täckström et al., 2015).”
Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling (2018, methodology): “1 Tan et al. (2018) 84.”