Abstract
It has been shown that transition-based methods can be used for syntactic word ordering and tree linearization, achieving significantly faster speed compared with traditional best-first methods. State-of-the-art transitionbased models give competitive results on abstract word ordering and unlabeled tree linearization, but significantly worse results onlabeled tree linearization. We demonstrate that
the main cause for the performance bottleneck is the sparsity of SHIFT transition actions rather than heavy pruning. To address this issue, we propose a modification to the standard transition-based feature structure, which
reduces feature sparsity and allows lookahead features at a small cost to decoding efficiency. Our model gives the best reported accuracies
on all benchmarks, yet still being over 30 times faster compared with best-first-search
the main cause for the performance bottleneck is the sparsity of SHIFT transition actions rather than heavy pruning. To address this issue, we propose a modification to the standard transition-based feature structure, which
reduces feature sparsity and allows lookahead features at a small cost to decoding efficiency. Our model gives the best reported accuracies
on all benchmarks, yet still being over 30 times faster compared with best-first-search
| Originalsprog | Engelsk |
|---|---|
| Titel | Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies |
| Forlag | Association for Computational Linguistics |
| Publikationsdato | 2016 |
| Sider | 488-493 |
| DOI | |
| Status | Udgivet - 2016 |
| Udgivet eksternt | Ja |