In-Order Chart-Based Constituent Parsing
This work addresses the problem of improving constituent parsing accuracy for natural language processing applications, offering an incremental improvement over existing chart-based methods.
This paper introduces a new in-order chart-based model for constituent parsing, which leverages in-order tree traversal for richer features and lookahead. The model achieved competitive performance on the Penn Treebank, outperforming previous chart-based models.
We propose a novel in-order chart-based model for constituent parsing. Compared with previous CKY-style and top-down models, our model gains advantages from in-order traversal of a tree (rich features, lookahead information and high efficiency) and makes a better use of structural knowledge by encoding the history of decisions. Experiments on the Penn Treebank show that our model outperforms previous chart-based models and achieves competitive performance compared with other discriminative single models.