Parsing as Reduction
This work addresses parsing challenges in natural language processing, particularly for discontinuous structures, offering a novel reduction method that is incremental in its application of existing dependency parsers.
The paper tackles the problem of phrase-representation parsing by reducing it to dependency parsing using a new intermediate representation called 'head-ordered dependency trees', which are isomorphic to constituent trees. The result shows that this approach achieves performance on par with strong baselines for English and surpasses the state of the art for discontinuous parsing of German by a wide margin.
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.