Notes About a More Aware Dependency Parser
This addresses a specific bottleneck in dependency parsing for NLP applications, but appears incremental as it builds on existing approaches.
The paper tackles the problem of assessing reliability in data-driven transition-based dependency parsers, which is crucial for downstream applications requiring correct parsing results, by proposing a novel parser model that combines transition-based and constraint-based approaches to operate in a 'more aware' and 'robust' manner.
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.