Semi-Supervised Semantic Role Labeling
By Hagen Fürstenau, Mirella Lapata. 2009
62 citations recorded by the source corpus.
Large scale annotated corpora are prerequisite to developing high-performance semantic role labeling systems. Unfortunately, such corpora are expensive to produce, limited in size, and may not be representative. Our work aims to reduce the annotation effort involved in creating resources for semantic role labeling via semi-supervised learning. Our algorithm augments a small number of manually labeled instances with unlabeled examples whose roles are inferred automatically via annotation projection. We formulate the projection task as a generalization of the linear assignment problem. We seek to find a role assignment in the unlabeled data such that the argument similarity between the labeled and unlabeled instances is maximized. Experimental results on semantic role labeling show that the automatic annotations produced by our method improve performance over using hand-labeled instances alone.
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
- Mohit Bansal
- Danai Koutra
- Leman Akoglu
- Mirella Lapata
- Hanghang Tong
- Richard Socher
- Jianfeng Gao
- Tina Eliassi-Rad
Citations in the corpus
- Automatically Learning Data Augmentation Policies for Dialogue Tasks (2019, positive): “There has been extensive work that employs data augmentation in both computer vision (Simard et al., 2003; Krizhevsky et al., 2012; Cires¸an et al., 2012; Wan et al., 2013; Sato et al., 2015; DeVries and Taylor, 2017; Tran et al., 2017; Lemley et al., 2017) and NLP (F¨urstenau and Lapata, 2009; Sen-”
- RolX: structural role extraction & mining in large graphs (2012, methodology): “Different approaches have been used for role discovery, including Bayesian frameworks using MCMC sampling algorithm for learning multiple roles of data points [28], semi-supervised semantic role labeling [11], etc.”
- Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations (2018, unknown): “…by us-ing synonym lists (Zhang et al., 2015; Wang and Yang, 2015), grammar induction (Jia and Liang, 2016), task-specific heuristic rules (F¨urstenau and Lapata, 2009; Kafle et al., 2017; Silfver-berg et al., 2017), or neural decoders of au-toencoders (Bergmanis et al., 2017; Xu et al.,…”
- Composition in Distributional Models of Semantics (2010, background): “, 2004) and semantic role labelling (Fürstenau and Lapata, 2009).”