Wc develop a l)ata-Oricntcd Parsing (DOP) model based on the syntactic representations of Lexicalf;unctional Grammar (LFG). We start by summarizing the original DOP model for tree...
We present an empirical study of the applicability of Probabilistic Lexicalized Tree Insertion Grammars (PLTIG), a lexicalized counterpart to Probabilistic Context-Free Grammars (...
In this paper, a computational approach for resolving zero-pronouns in Spanish texts is proposed. Our approach has been evaluated with partial parsing of the text and the results ...
Bootstrapping semantics from text is one of the greatest challenges in natural language learning. We first define a word similarity measure based on the distributional pattern of ...
Bagging and boosting, two effective machine learning techniques, are applied to natural language parsing. Experiments using these techniques with a trainable statistical parser ar...