Extended Abstract

Empty Categories Help Parse the Overt

---

Abstract

This paper is concerned with whether deep syntactic information can help surface parsing, with a particular focus on empty categories. We consider data-driven dependency parsing with both linear and neural disambiguation models. We find that the information about empty categories is helpful to reduce the approximation error in a structured prediction based parsing model, but increases the search space for inference and accordingly the estimation error. To deal with structure-based overfitting, we propose to integrate disambiguation models with and without empty elements. Experiments on English and Chinese TreeBanks indicate that incorporating empty elements consistently improves surface parsing.

Keywords: Empty Category, Dependency Parsing

How to Cite:

Sun, W., (2019) “Empty Categories Help Parse the Overt”, Society for Computation in Linguistics 2(1), 298-301. doi: https://doi.org/10.7275/s40b-cr80