Span-Based LCFRS-2 Parsing
Miloš Stanojević, Mark J. Steedman · 2020
The earliest models for discontinuous constituency parsers used mildly context-sensitive grammars, but the fashion has changed in recent years to grammar-less transition-based parsers that use strong neural probabilistic models to greedily predict transitions.We also show that the main bottleneck for further improvement in performance is in the restriction of fan-out to degree 2. We show that well-nestedness is helpful in speeding up parsing, but lowers accuracy.