UniParse: A universal graph-based parsing toolkit
This toolkit addresses the need for efficient and extensible tools in dependency parsing research, though it is incremental as it builds on existing methods.
The paper introduces UniParse, a universal graph-based parsing toolkit that streamlines research prototyping, development, and evaluation of dependency parsing architectures by providing efficient, extensible implementations of all parser components, including re-implementations of current state-of-the-art first-order graph-based parsers.
This paper describes the design and use of the graph-based parsing framework and toolkit UniParse, released as an open-source python software package. UniParse as a framework novelly streamlines research prototyping, development and evaluation of graph-based dependency parsing architectures. UniParse does this by enabling highly efficient, sufficiently independent, easily readable, and easily extensible implementations for all dependency parser components. We distribute the toolkit with ready-made configurations as re-implementations of all current state-of-the-art first-order graph-based parsers, including even more efficient Cython implementations of both encoders and decoders, as well as the required specialised loss functions.