Abstract | Binarization of grammars is crucial for improving the complexity and performance of parsing and translation. |
Abstract | We present a versatile binarization algorithm that can be tailored to a number of grammar formalisms by simply varying a formal parameter. |
Abstract | We apply our algorithm to binarizing tree-to-string transducers used in syntax-based machine translation. |
Introduction | Binarization amounts to transforming a given grammar into an equivalent grammar of rank 2, i.e., with at most two nonterminals on any right-hand side. |
Introduction | The ability to binarize grammars is crucial for efficient parsing, because for many grammar formalisms the parsing complexity depends exponentially on the rank of the grammar. |
Introduction | The classical approach to binarization , as known from the Chomsky normal form transformation for context-free grammars (CFGs), proceeds rule by rule. |
Features | Note that after binarization , grandparent and sibling information becomes very important in encoding the structure. |
Implementation | This section introduces important implementation details, including supertagging, feature forest pruning and binarization methods. |
Implementation | 5.3 Binarization |
Implementation | Since Penn Treebank trees are not binarized, we construct a simple procedure for binarizing them. |
The Learning Problem | Note that the two derivations share the same ( binarized ) tree structure. |
Character-based Chinese Parsing | The system can provide bina-rzied CFG trees in Chomsky Norm Form, and they present a reversible conversion procedure to map arbitrary CFG trees into binarized trees. |
Character-based Chinese Parsing | In this work, we remain consistent with their work, using the head-finding rules of Zhang and Clark (2008), and the same binarization algorithm.1 We apply the same beam-search algorithm for decoding, and employ the averaged perceptron with early-update to train our model. |
Word Structures and Syntax Trees | Our annotations are binarized recursive word |
Word Structures and Syntax Trees | (Los Angeles)”, have flat structures, and we use “coordination” for their left binarization . |
Abstract | We present a more precise characterization of the algorithm’s complexity, an optimization analogous to binarization of context-free grammars, and some important implementation details, resulting in an algorithm that is practical for natural-language applications. |
Introduction | We give a more precise complexity analysis in terms of the grammar and the size and maximum degree of the input graph, and we show how to optimize it by a process analogous to binarization of CFGs, following Gildea (2011). |
Parsing | In this section, we present a refinement that makes the rule-matching procedure explicit, and because it matches rules little by little, similarly to binarization of CFG rules, it does so more efliciently than the original. |