Dependency Parsing with Compression Rules

Abstract

This article proposes a syntactic parsing strategy based on a dependency grammar containing both formal rules and a compression technique that reduces the complexity of those rules. Compression parsing is mainly driven by the single-head constraint of Dependency Grammar, and can be seen as an alternative method to the well-known constructive strategy. The compression algorithm simplifies the input sentence by progressively removing from it the dependent tokens as soon as binary syntactic dependencies are recognized. The performance of our system was compared to a deterministic parser based on supervised learning: MaltParser. Both systems were applied on several test sets of sentences in Spanish and Portuguese, from a variety of different domains and genres. Results showed that our parsing method keeps a similar performance through related languages and different domains, while MaltParser, as most supervised methods, turns out to be very dependent on the text domain used to train the system.