Køpsala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding
This work addresses parsing challenges in computational linguistics, but it is incremental as it builds on existing methods.
The paper tackled enhanced graph parsing for Universal Dependencies by adapting a transition-based parser, achieving 4th place in the IWPT 2020 shared task after fixing a bug, with results measured by average ELAS.
We present Køpsala, the Copenhagen-Uppsala system for the Enhanced Universal Dependencies Shared Task at IWPT 2020. Our system is a pipeline consisting of off-the-shelf models for everything but enhanced graph parsing, and for the latter, a transition-based graph parser adapted from Che et al. (2019). We train a single enhanced parser model per language, using gold sentence splitting and tokenization for training, and rely only on tokenized surface forms and multilingual BERT for encoding. While a bug introduced just before submission resulted in a severe drop in precision, its post-submission fix would bring us to 4th place in the official ranking, according to average ELAS. Our parser demonstrates that a unified pipeline is effective for both Meaning Representation Parsing and Enhanced Universal Dependencies.