We present a linguistically-motivated algorithm for reconstructing nonlocal dependency in broad-coverage context-free parse trees derived from treebanks. We use an algorithm based...
Since 1995, a few statistical parsing algorithms have demonstrated a breakthrough in parsing accuracy, as measured against the UPenn TREEBANK as a gold standard. In this paper we ...
Scott Miller, Heidi Fox, Lance A. Ramshaw, Ralph M...
We describe the use of energy function optimisation in very shallow syntactic parsing. The approach can use linguistic rules and corpus-based statistics, so the strengths of both ...
We present a preliminary study of several parser adaptation es evaluated on the GENIA corpus of MEDLINE abstracts [1,2]. We begin by observing that the Penn Treebank (PTB) is lexic...