SETUP: Sentence-level English-To-Uniform Meaning Representation Parser
This work addresses the need for scalable UMR parsing to enable applications in language documentation and low-resource language technologies, but it is incremental as it builds on existing parsers and converters.
The paper tackles the problem of automatically parsing English text into Uniform Meaning Representation (UMR) graphs, which are semantic representations for diverse languages, and achieves an AnCast score of 84 and a SMATCH++ score of 91 with their best model, SETUP.
Uniform Meaning Representation (UMR) is a novel graph-based semantic representation which captures the core meaning of a text, with flexibility incorporated into the annotation schema such that the breadth of the world's languages can be annotated (including low-resource languages). While UMR shows promise in enabling language documentation, improving low-resource language technologies, and adding interpretability, the downstream applications of UMR can only be fully explored when text-to-UMR parsers enable the automatic large-scale production of accurate UMR graphs at test time. Prior work on text-to-UMR parsing is limited to date. In this paper, we introduce two methods for English text-to-UMR parsing, one of which fine-tunes existing parsers for Abstract Meaning Representation and the other, which leverages a converter from Universal Dependencies, using prior work as a baseline. Our best-performing model, which we call SETUP, achieves an AnCast score of 84 and a SMATCH++ score of 91, indicating substantial gains towards automatic UMR parsing.