A Generative Model for Semantic Role Labeling
Abstract
Determining the semantic role of sentence constituents is a key task in determining sentence meanings lying behind a veneer of variant syntactic expression. We present a model of natural language generation from semantics using the FrameNet semantic role and frame ontology. We train the model using the FrameNet corpus and apply it to the task of automatic semantic role and frame identification, producing results competitive with previous work (about 70% role labeling accuracy). Unlike previous models used for this task, our model does not assume that the frame of a sentence is known, and is able to identify null-instantiated roles , which commonly occur in our corpus and whose identification is crucial to natural language interpretation.
Cite
Text
Thompson et al. "A Generative Model for Semantic Role Labeling." European Conference on Machine Learning, 2003. doi:10.1007/978-3-540-39857-8_36Markdown
[Thompson et al. "A Generative Model for Semantic Role Labeling." European Conference on Machine Learning, 2003.](https://mlanthology.org/ecmlpkdd/2003/thompson2003ecml-generative/) doi:10.1007/978-3-540-39857-8_36BibTeX
@inproceedings{thompson2003ecml-generative,
title = {{A Generative Model for Semantic Role Labeling}},
author = {Thompson, Cynthia A. and Levy, Roger and Manning, Christopher D.},
booktitle = {European Conference on Machine Learning},
year = {2003},
pages = {397-408},
doi = {10.1007/978-3-540-39857-8_36},
url = {https://mlanthology.org/ecmlpkdd/2003/thompson2003ecml-generative/}
}