The Effect of Syntactic Representation on Semantic Role Labeling
By Richard Johansson, Pierre Nugues. 2008
87 citations recorded by the source corpus.
Almost all automatic semantic role labeling (SRL) systems rely on a preliminary parsing step that derives a syntactic structure from the sentence being analyzed. This makes the choice of syntactic representation an essential design decision. In this paper, we study the influence of syntactic representation on the performance of SRL systems. Specifically, we compare constituent-based and dependency-based representations for SRL of English in the FrameNet paradigm. Contrary to previous claims, our results demonstrate that the systems based on dependencies perform roughly as well as those based on constituents: For the argument classification task, dependency-based systems perform slightly higher on average, while the opposite holds for the argument identification task. This is remarkable because dependency parsers are still in their infancy while constituent parsing is more mature. Furthermore, the results show that dependency-based semantic role classifiers rely less on lexicalized features, which makes them more robust to domain changes and makes them learn more efficiently with respect to the amount of training data.
Subfields: Artificial Intelligence
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
- Ivan Titov
- Diego Marcheggiani
- Alessandro Moschitti
- Danilo Croce
- Roberto Basili
- Oren Etzioni
- Mausam
- Stephen Soderland
Citations in the corpus
- Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling (2017, background): “Though historically most SRL approaches did rely on syntax (Thompson et al., 2003; Pradhan et al., 2005; Punyakanok et al., 2008; Johansson and Nugues, 2008), the last generation of SRL models put syntax aside in favor of neural sequence models, namely LSTMs (Zhou and Xu, 2015; Marcheggiani et al.”
- Structured Lexical Similarity via Convolution Kernels on Dependency Trees (2011, methodology): “We used the FrameNet version 1.3 with the 90/10% split between training and test set (i.e 271,560 and 30,173 examples respectively), as de-fined in (Johansson and Nugues, 2008b), one of the best system for FrameNet parsing.”
- ReNoun: Fact Extraction for Nominal Attributes (2014, background): “State of the art SRL systems, such as that of Johansson and Nugues (2008), are trained on NomBank (Meyers et al., 2004) for handling nominal relations, which also means that they are limited by the knowledge it has.”
- Open Language Learning for Information Extraction (2012, methodology): “For comparison, we use a state-of-the-art SRL system from Lund University (Johansson and Nugues, 2008), which is trained on PropBank (Martha and Palmer, 2002) for its verb-frames and NomBank (Meyers et al., 2004) for noun-frames.”