Semantic Role Chunking Combining Complementary Syntactic Views

By Sameer Pradhan, Kadri Hacioglu, Wayne H. Ward, James H. Martin, Dan Jurafsky. 2005

82 citations recorded by the source corpus.

This paper describes a semantic role labeling system that uses features derived from different syntactic views, and combines them within a phrase-based chunking paradigm. For an input sentence, syntactic constituent structure parses are generated by a Charniak parser and a Collins parser. Semantic role labels are assigned to the constituents of each parse using Support Vector Machine classifiers. The resulting semantic role labels are converted to an IOB representation. These IOB representations are used as additional features, along with flat syntactic chunks, by a chunking SVM classifier that produces the final SRL output. This strategy for combining features from three different syntactic views gives a significant improvement in performance over roles produced by using any one of the syntactic views individually.

Subfields: Artificial Intelligence, Natural Language Processing, Information Extraction

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

In Information Extraction

Citations in the corpus

Natural Language Processing (Almost) from Scratch (2011, methodology): “3) 94.29% Kudo and Matsumoto (2001) 93.91% (b) CHUNK System F1 Ando and Zhang (2005) 89.31% Florian et al. (2003) 88.76% Kudo and Matsumoto (2001) 88.31% (c) NER System F1 Koomen et al. (2005) 77.92% Pradhan et al. (2005) 77.30% Haghighi et al. (2005) 77.04% (d) SRL Table 2: State-of-the-art systems”
End-to-end learning of semantic role labeling using recurrent neural networks (2015, methodology): “The analysis in (Pradhan et al., 2005) found that the major source of the incorrect predictions was the syntactic parser.”
Deep Semantic Role Labeling: What Works and What’s Next (2017, neutral): “We are also able to compare to previous systems whose model predictions are available online (Punyakanok et al., 2005; Pradhan et al., 2005).”
Introduction to the CoNLL-2005 Shared Task: Semantic Role Labeling (2005, methodology): “Their results on the WSJ test equal the best results published so far on this task and datasets (Pradhan et al., 2005a), though they are not directly comparable due to a different setting in deﬁning arguments not perfectly matching the predicted parse constituents.”
Deep Semantic Role Labeling with Self-Attention (2017, background): “Pradhan et al. (2005); Surdeanu et al. (2003); Palmer, Gildea, and Xue (2010) explored the syntactic features for capturing the overall sentence structure.”
Neural Semantic Role Labeling with Dependency Path Embeddings (2016, background): “Most semantic role labeling approaches to date rely heavily on lexical and syntactic indicator features.”
Robust Parsing of the Proposition Bank (2006, methodology): “Accordingly, it is not possible to draw a straigthforward quantitative F R P (Haghighi et al., 2005) 83.4 83.1 83.7 (Pradhan et al., 2005) 83.3 83.0 83.5 (Punyakanok et al., 2005) 83.1 82.8 83.3 (Marquez et al., 2005) 83.1 82.8 83.3 (Surdeanu and Turmo, 2005) , 1999; Charniak, 2000), both for…”
The Importance of Syntactic Parsing and Inference in Semantic Role Labeling (2008, methodology): “A related comparison can be found also in the work by Pradhan et al. (2005) (their earlier version appeared in (Pradhan et al., 2003)) which reported the performance on several systems using different information sources and system architectures.”
Special Issue Introduction: Semantic Role Labeling: An Introduction to the Special Issue (2008, unknown): “Finally, probabilistic models have also been applied to produce the structured output, for example, generative models (Thompson, Levy, and Manning 2003), sequence tagging with classifiers (Màrquez et al. 2005; Pradhan et al. 2005b), and Conditional Random Fields on tree structures (Cohn and Blunsom ”