This paper presents a novel method for wide coverage parsing using an incremental strategy, which is psycholinguistically motivated. A recursive neural network is trained on treeba...
Fabrizio Costa, Vincenzo Lombardo, Paolo Frasconi,...
The integration of multiword expressions in a parsing procedure has been shown to improve accuracy in an artiļ¬cial context where such expressions have been perfectly pre-identiļ...
Matthieu Constant, Anthony Sigogne, Patrick Watrin
We present evidence that head-driven parsing strategies lead to efficiency gains over standard parsing strategies, for lexicalist, concatenative and unification-based grammars. A ...
We describe the parser of LEU/2, the Linguistic Experimentation Environment of the LILOG project. The parser is designed to support and encourage experimentation with different gr...
The present work advances the accuracy and training speed of discriminative parsing. Our discriminative parsing method has no generative component, yet surpasses a generative base...