This paper proposes a method to improve shift-reduce constituency parsing by using lexical dependencies. The lexical dependency information is obtained from a large amount of auto-parsed data that is generated by a baseline shift-reduce parser on unlabeled data. We then incorporate a set of novel features defined on this information into the shift-reduce parsing model. The features can help to ...

Humans are unique in their propensity for helping. Not only do we help others in need by reacting to their requests, we also help proactively by assisting in the absence of a request. Proactive helping requires the actor to detect the need for help, recognize the intention of the other, and remedy the situation. Very little is known about the development of this social phenomenon beyond an urba...

We propose an algorithm for coreference resolution based on analogy with shift-reduce parsing. By reconceptualising the task in this way, we unite rankingand cluster-based approaches to coreference resolution, which have until now been largely orthogonal. Additionally, our framework naturally lends itself to rich discourse modelling, which we use to define a series of psycholinguistically motiv...

bridges, as an essential part of transportation system, play a special role in economy, politic and military all around the world. serviceability of bridges is of high importance especially in emergencies, helping injured people and proportioning transportation after earthquakes. earthquake regulation codes, normally suggest linear methods to conduct the analysis, and nonlinear analysis is bare...