Universal Dependency Parsing with a General Transition-Based DAG Parser
This work addresses parsing challenges for linguists and NLP researchers by applying a general parser to UD, but it is incremental as it adapts an existing method to new data without major innovations.
The paper tackled the problem of parsing Universal Dependencies (UD) by adapting TUPA, a neural transition-based DAG parser originally designed for UCCA, to handle UD trees and graphs, achieving results in the CoNLL 2018 shared task, including the first experiments on recovering enhanced dependencies.
This paper presents our experiments with applying TUPA to the CoNLL 2018 UD shared task. TUPA is a general neural transition-based DAG parser, which we use to present the first experiments on recovering enhanced dependencies as part of the general parsing task. TUPA was designed for parsing UCCA, a cross-linguistic semantic annotation scheme, exhibiting reentrancy, discontinuity and non-terminal nodes. By converting UD trees and graphs to a UCCA-like DAG format, we train TUPA almost without modification on the UD parsing task. The generic nature of our approach lends itself naturally to multitask learning. Our code is available at https://github.com/CoNLL-UD-2018/HUJI