Abstract
We develop parsing oracles for two transition-based dependency parsers, including the arc-standard parser, solving a problem that was left open in (Goldberg and Nivre, 2013). We experimentally show that using these oracles in training yields superior parsing accuracies on many languages.
Original language | American English |
---|---|
Pages (from-to) | 119-130 |
Number of pages | 12 |
Journal | Transactions of the Association for Computational Linguistics |
Volume | 2 |
State | Published - 2014 |