Corrective Modeling for Non-Projective Dependency Parsing
نویسندگان
چکیده
We present a corrective model for recovering non-projective dependency structures from trees generated by state-of-theart constituency-based parsers. The continuity constraint of these constituencybased parsers makes it impossible for them to posit non-projective dependency trees. Analysis of the types of dependency errors made by these parsers on a Czech corpus show that the correct governor is likely to be found within a local neighborhood of the governor proposed by the parser. Our model, based on a MaxEnt classifier, improves overall dependency accuracy by .7% (a 4.5% reduction in error) with over 50% accuracy for non-projective structures.
منابع مشابه
Corrective Dependency Parsing
We present a discriminative model for correcting errors in automatically generated dependency trees. We show that by focusing on “structurally local” errors, we can improve the overall quality of the dependency structure. Defining the task by way of a locality constraint allows us to search over a large set of alternate dependency trees simply by making small perturbations to individual depende...
متن کاملA Three-Step Transition-Based System for Non-Projective Dependency Parsing
This paper presents a non-projective dependency parsing system that is transition-based and operates in three steps. The three steps include one classical method for projective dependency parsing and two inverse methods predicting separately the right and left non-projective dependencies. Splitting the parsing allows to increase the scores on both projective and non-projective dependencies comp...
متن کاملPseudo-Projective Dependency Parsing
In order to realize the full potential of dependency-based syntactic parsing, it is desirable to allow non-projective dependency structures. We show how a datadriven deterministic dependency parser, in itself restricted to projective structures, can be combined with graph transformation techniques to produce non-projective structures. Experiments using data from the Prague Dependency Treebank s...
متن کاملOn the Complexity of Non-Projective Data-Driven Dependency Parsing
In this paper we investigate several nonprojective parsing algorithms for dependency parsing, providing novel polynomial time solutions under the assumption that each dependency decision is independent of all the others, called here the edge-factored model. We also investigate algorithms for non-projective parsing that account for nonlocal information, and present several hardness results. This...
متن کاملComparing Non-projective Strategies for Labeled Graph-Based Dependency Parsing
We fill a gap in the systematically analyzed space of available techniques for state-of-the-art dependency parsing by comparing non-projective strategies for graph-based parsers. Using three languages with varying frequency of non-projective constructions, we compare the non-projective approximation algorithm with pseudo-projective parsing. We also analyze the differences between different enco...
متن کامل