Labeling the Semantic Roles of Commas

Abstract

Commas and the surrounding sentence structure often express relations that are essential to understanding the meaning of the sentence. This paper proposes a set of relations commas participate in, expanding on previous work in this area, and develops a new dataset annotated with this set of labels. We identify features that are important to achieve a good performance on comma labeling and then develop a machine learning method that achieves high accuracy on identifying comma relations, improving over previous work. Finally, we discuss a variety of possible uses, both as syntactic and discourse-oriented features and constraints for downstream tasks.

Cite

Text

Arivazhagan et al. "Labeling the Semantic Roles of Commas." AAAI Conference on Artificial Intelligence, 2016. doi:10.1609/AAAI.V30I1.10395

Markdown

[Arivazhagan et al. "Labeling the Semantic Roles of Commas." AAAI Conference on Artificial Intelligence, 2016.](https://mlanthology.org/aaai/2016/arivazhagan2016aaai-labeling/) doi:10.1609/AAAI.V30I1.10395

BibTeX

@inproceedings{arivazhagan2016aaai-labeling,
  title     = {{Labeling the Semantic Roles of Commas}},
  author    = {Arivazhagan, Naveen and Christodoulopoulos, Christos and Roth, Dan},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2016},
  pages     = {2885-2891},
  doi       = {10.1609/AAAI.V30I1.10395},
  url       = {https://mlanthology.org/aaai/2016/arivazhagan2016aaai-labeling/}
}