Transducing Sentences to Syntactic Feature Vectors: an Alternative Way to "Parse"?
Fabio Massimo Zanzotto, Lorenzo Dell’Arciprete · Cineca Institutional Research Information System (Tor Vergata University) · 2013
Classification and learning algorithms use syntactic structures as proxies between source sentences and feature vectors. In this paper, we explore an alternative path to use syntax in feature spaces: the Distributed Representation “Parsers” (DRP). The core of the idea is straightforward: DRPs directly obtain syntactic feature vectors from sentences without explicitly producing symbolic syntactic interpretations. Results show that DRPs produce feature spaces significantly better than those obtained by existing methods in the same conditions and competitive with those obtained by existing methods with lexical information.