Dependency-based Semantic Role Labeling of PropBank

By Richard Johansson, Pierre Nugues. 2008

138 citations recorded by the source corpus.

We present a PropBank semantic role labeling system for English that is integrated with a dependency parser. To tackle the problem of joint syntactic--semantic analysis, the system relies on a syntactic and a semantic subcomponent. The syntactic model is a projective parser using pseudo-projective transformations, and the semantic model uses global inference mechanisms on top of a pipeline of classifiers. The complete syntactic-semantic output is selected from a candidate pool generated by the subsystems. We evaluate the system on the CoNLL-2005 test sets using segment-based and dependency-based metrics. Using the segment-based CoNLL-2005 metric, our system achieves a near state-of-the-art F1 figure of 77.97 on the WSJ+Brown test set, or 78.84 if punctuation is treated consistently. Using a dependency-based metric, the F1 figure of our system is 84.29 on the test set from CoNLL-2008. Our system is the first dependency-based semantic role labeler for PropBank that rivals constituent-based systems in terms of performance.

Subfields: Artificial Intelligence, Natural Language Processing

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 Natural Language Processing

Citations in the corpus

The Natural Language Decathlon: Multitask Learning as Question Answering (2018, background): “Semantic role labeling (SRL) models are given a sentence and predicate (typically a verb) and must determine ‘who did what to whom,’ ‘when,’ and ‘where’ [Johansson and Nugues, 2008].”
Linguistically-Informed Self-Attention for Semantic Role Labeling (2018, methodology): “We train the model using the Nadam (Dozat, 2016) algorithm for adaptive stochastic gradient descent (SGD), which combines Adam (Kingma and Ba, 2015) SGD with Nesterov momentum (Nesterov, 1983).”
Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking (2020, result): “We now turn to the GNN-based SRL system of Marcheggiani & Titov (2017).”
Frame-Semantic Parsing (2014, methodology): “We also labeled each verb in the data as having ACTIVE or PASSIVE voice, using code from the SRL system described by Johansson and Nugues (2008).”
Efficient Inference and Structured Learning for Semantic Role Labeling (2015, background): “Another popular approach has been to apply a reranking model, which can incorporate soft structural constraints in the form of features, on top of the k-best output of local classifiers (Toutanova et al., 2008; Johansson and Nugues, 2008).”