Abstract
This paper is concerned with whether deep syntactic information can help surface parsing, with a particular focus on empty categories. We design new algorithms to produce dependency trees in which empty elements are allowed, and evaluate the impact of information about empty category on parsing overt elements. Such information is helpful to reduce the approximation error in a structured 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, and perform structure regularization via joint decoding. Experiments on English and Chinese TreeBanks with different parsing models indicate that incorporating empty elements consistently improves surface parsing.
Highlights
In the last two decades, there was an increasing interest in producing rich syntactic annotations that are not limited to surface analysis
Deep grammar formalisms allow information beyond local construction to be constructed, it is still not clear whether such additional information is helpful for surface syntactic analysis
We use the tool provided by Stanford CoreNLP to process Penn TreeBank (PTB), and the tool provided by Xue and Yang (2013) to process Chinese TreeBank (CTB) 5.0
Summary
In the last two decades, there was an increasing interest in producing rich syntactic annotations that are not limited to surface analysis. The new representation provides a considerable amount of deep syntactic information, while keeping intact all dependencies of overt words Integrating both overt and covert elements in one unified representation provides an effective yet lightweight way to achieve deeper language understanding beyond surface syntax. Integrating both overt and covert elements in one unified representation provides an effective yet lightweight way to achieve deeper language understanding beyond surface syntax1 Even more important, this modest way to modify tree analysis makes possible fair evaluation of the influence of deep syntactic elements on surface parsing
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
