We present a connectionist architecture and demonstrate that it can learn syntactic parsing from a corpus of parsed text. The architecture can represent syntactic constituents, an...
This paper proposes a new class-based method to estimate the strength of association in word co-occurrence for the purpose of structural disambiguation. To deal with sparseness of...
An efficient use of lexical cohesion is described for ranking text units according to their contribution in defining the meaning of a text (textual saliency), their ability to for...
Concerning different approaches to automatic PoS tagging: EngCG-2, a constraintbased morphological tagger, is compared in a double-blind test with a state-of-the-art statistical t...
We present an algorithm for simultaneously constructing both the syntax and semantics of a sentence using a Lexicalized Tree Adjoining Grammar (LTAG). This approach captures natur...