Parsing Universal Dependencies without training
This provides a linguistically sound unsupervised baseline for cross-lingual parsing in Universal Dependencies, though it is incremental as it builds on existing methods like PageRank.
The authors tackled the problem of parsing Universal Dependencies without training data by proposing UDP, a training-free parser based on PageRank and head attachment rules, which is competitive with a delexicalized transfer system.
We propose UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of head attachment rules. It features two-step decoding to guarantee that function words are attached as leaf nodes. The parser requires no training, and it is competitive with a delexicalized transfer system. UDP offers a linguistically sound unsupervised alternative to cross-lingual parsing for UD, which can be used as a baseline for such systems. The parser has very few parameters and is distinctly robust to domain change across languages.