Parsing as Reduction

TL;DR

This paper introduces a novel reduction from phrase-structure parsing to dependency parsing using head-ordered dependency trees, enabling effective discontinuous parsing and achieving state-of-the-art results.

Contribution

It presents a new isomorphic intermediate representation and a method to leverage existing dependency parsers for constituent parsing, including discontinuous structures.

Findings

Parsers achieve performance comparable to strong baselines.

State-of-the-art results in German discontinuous parsing.

Effective use of non-projective dependency parsing for constituency tasks.

Abstract

We reduce phrase-representation parsing to dependency parsing. Our reduction is grounded on a new intermediate representation, "head-ordered dependency trees", shown to be isomorphic to constituent trees. By encoding order information in the dependency labels, we show that any off-the-shelf, trainable dependency parser can be used to produce constituents. When this parser is non-projective, we can perform discontinuous parsing in a very natural manner. Despite the simplicity of our approach, experiments show that the resulting parsers are on par with strong baselines, such as the Berkeley parser for English and the best single system in the SPMRL-2014 shared task. Results are particularly striking for discontinuous parsing of German, where we surpass the current state of the art by a wide margin.