Notes About a More Aware Dependency Parser

TL;DR

This paper discusses developing a more aware dependency parser that combines data-driven and constraint-based methods to improve reliability and robustness in parsing results.

Contribution

It introduces a novel parser model that integrates strengths of different approaches for more reliable and robust dependency parsing.

Findings

Proposes a new parser model with enhanced awareness.

Addresses reliability issues in transition-based parsing.

Aims for more robust dependency analysis.

Abstract

In this paper I explain the reasons that led me to research and conceive a novel technology for dependency parsing, mixing together the strengths of data-driven transition-based and constraint-based approaches. In particular I highlight the problem to infer the reliability of the results of a data-driven transition-based parser, which is extremely important for high-level processes that expect to use correct parsing results. I then briefly introduce a number of notes about a new parser model I'm working on, capable to proceed with the analysis in a "more aware" way, with a more "robust" concept of robustness.