A Span Selection Model for Semantic Role Labeling

2018/10/04 by Hiroki Ouchi, Hiroyuki Shindo, Ouchi, Hiroki +3
Biochemistry, Genetics and Molecular Biology · Computer Science · #Biomedical Text Mining and Ontologies #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1810.02245

openalex publication_date 2018/10/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present a simple and accurate span-based model for semantic role labeling (SRL). Our model directly takes into account all possible argument spans and scores them for each label. At decoding time, we greedily select higher scoring labeled spans. One advantage of our model is to allow us to design and use span-level features, that are difficult to use in token-based BIO tagging approaches. Experimental results demonstrate that our ensemble model achieves the state-of-the-art results, 87.4 F1 and 87.0 F1 on the CoNLL-2005 and 2012 datasets, respectively.

Citations

• Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
• Bidirectional recurrent neural networks
• Close Yet Distinctive Domain Adaptation
• Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold
• Constituency Parsing with a Self-Attentive Encoder

Related

• Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling
• How to best use Syntax in Semantic Role Labelling
• Dependency and Span, Cross-Style Semantic Role Labeling on PropBank and NomBank
• Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments
• A Systematic Survey of Semantic Role Labeling in the Era of Pretrained Language Models