A Unifying Theory of Transition-based and Sequence Labeling Parsing
This work provides a unifying framework for parsing researchers, though it is incremental as it builds on existing transition-based parsers.
The paper establishes a theoretical mapping between transition-based and sequence-labeling parsing, enabling new encodings for fast parsing, and demonstrates this in dependency parsing with four algorithms achieving comparable performance to existing methods.
We define a mapping from transition-based parsing algorithms that read sentences from left to right to sequence labeling encodings of syntactic trees. This not only establishes a theoretical relation between transition-based parsing and sequence-labeling parsing, but also provides a method to obtain new encodings for fast and simple sequence labeling parsing from the many existing transition-based parsers for different formalisms. Applying it to dependency parsing, we implement sequence labeling versions of four algorithms, showing that they are learnable and obtain comparable performance to existing encodings.