Dependency Graph Parsing as Sequence Labeling
This work addresses the limitation of existing sequence labeling methods for dependency parsing, enabling more efficient and accurate graph parsing for NLP applications, though it is incremental in extending prior linearizations.
The paper tackled the problem of parsing complex graph-based dependencies like semantic dependencies and enhanced universal dependencies by extending sequence labeling linearizations to handle reentrancy and cycles, achieving accuracies close to state-of-the-art with high efficiency.
Various linearizations have been proposed to cast syntactic dependency parsing as sequence labeling. However, these approaches do not support more complex graph-based representations, such as semantic dependencies or enhanced universal dependencies, as they cannot handle reentrancy or cycles. By extending them, we define a range of unbounded and bounded linearizations that can be used to cast graph parsing as a tagging task, enlarging the toolbox of problems that can be solved under this paradigm. Experimental results on semantic dependency and enhanced UD parsing show that with a good choice of encoding, sequence-labeling dependency graph parsers combine high efficiency with accuracies close to the state of the art, in spite of their simplicity.