A structured account of compositional meaning has been longstanding goal for both natural language understanding and computational semantics. To this end, a number of efforts have focused on encoding semantic relationships and attributes in a semantic graph.

In these formalisms, semantic information is typically encoded discretely, using nominal category labels for nodes and edges. This categorical encoding can make such formalisms brittle when presented with non-prototypical instances, and leads to challenges in coping with changing label ontologies and new datasets. Furthermore, they are difficult to annotate, often requiring trained linguists and large annotation manuals.

We develop joint UDS parsers, which learns to extract both graph structures and attributes from natural language input.


Zhang, Sheng, Xutai Ma, Rachel Rudinger, Kevin Duh, and Benjamin Van Durme. 2018. Cross-lingual Semantic Parsing. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 1664-1675. Brussels, Belgium: Association for Computational Linguistics. [pdf, doi, bib]
Stengel-Eskin, Elias, Aaron Steven White, Sheng Zhang, and Benjamin Van Durme. 2020. Universal Decompositional Semantic Parsing. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 8427–8439. Online: Association for Computational Linguistics. [pdf, doi, bib]


Elias Stengel-Eskin bio photo
Elias Stengel-Eskin
Sheng Zhang bio photo
Sheng Zhang
Rachel Rudinger bio photo
Rachel Rudinger
Aaron Steven White bio photo
Aaron Steven White
Benjamin Van Durme bio photo
Benjamin Van Durme