A Systematic Comparison of Syntactic Representations of Dependency Parsing
This work addresses the impact of syntactic representation choices on dependency parsing accuracy for computational linguistics researchers, but it is incremental as it builds on existing methods without introducing new paradigms.
The study compared the performance of a transition-based parser across different syntactic annotation schemes in universal dependency treebanks, finding that standardizing certain constructions does not consistently improve parsing performance and that results vary significantly by language.
We compare the performance of a transition-based parser in regards to different annotation schemes. We pro-pose to convert some specific syntactic constructions observed in the universal dependency treebanks into a so-called more standard representation and to evaluate parsing performances over all the languages of the project. We show that the ``standard'' constructions do not lead systematically to better parsing performance and that the scores vary considerably according to the languages.