PredPatt is a framework for extracting extensible, interpretable, language-neutral predicate-argument patterns that bridge from the deep syntax of the Universal Dependency project to an initial shallow semantic layer. This shallow semantic layer forms the basis for Decomp-aligned semantic annotations on Universal Dependency treebanks and can be separately considered a linguistically well-founded component of a Universal IE system.



White, Aaron Steven, Dee Ann Reisinger, Keisuke Sakaguchi, Tim Vieira, Sheng Zhang, Rachel Rudinger, Kyle Rawlins, and Benjamin Van Durme. 2016. Universal Decompositional Semantics on Universal Dependencies. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 1713–1723. Austin, Texas: Association for Computational Linguistics. [pdf, doi, bib]
Zhang, Sheng, Rachel Rudinger, and Benjamin Van Durme, 2017. An evaluation of predpatt and open ie via stage 1 semantic role labeling. In IWCS 2017—12th International Conference on Computational Semantics—Short papers, 1-7. [pdf, doi, bib]


Sheng Zhang bio photo
Sheng Zhang
Rachel Rudinger bio photo
Rachel Rudinger
Benjamin Van Durme bio photo
Benjamin Van Durme