We describe a generative probabilistic model of natural language, which we call HBG, that takes advantage of detailed linguistic information to resolve ambiguity. HBG incorporates...
Ezra Black, Frederick Jelinek, John D. Lafferty, D...
Abstract. This paper introduces an approach to address the problem of accessing conventional and geographic data from the Deep Web. The approach relies on describing the relevant d...
Helena Piccinini, Melissa Lemos, Marco A. Casanova...
rder Abstract Categorial Grammars as Hyperedge Replacement Grammars Makoto Kanazawa National Institute of Informatics 2–1–2 Hitotsubashi, Chiyoda-ku, Tokyo, 101–8430, Japan A...
Standard ML employs an opaque (or generative) semantics of datatypes, in which every datatype declaration produces a new type that is different from any other type, including othe...
Joseph Vanderwaart, Derek Dreyer, Leaf Petersen, K...
One of the central problems in building broad-coverage story understanding systems is generating expectations about event sequences, i.e. predicting what happens next given some a...