Creating labeled training data for relation extraction is expensive. In this paper, we study relation extraction in a special weakly-supervised setting when we have only a few see...
We argue that the situation calculus is a natural formalism for representing and reasoning about control and strategic information. As a case study, in this paper we provide a sit...
-- This paper presents the current state of a work in progress, whose objective is to better understand the effects of factors that significantly influence the performance of the L...
Alain Lifchitz, Sandra Jhean-Larose, Guy Denhi&egr...
Abstract-- A large amount of the world's data is both sequential and imprecise. Such data is commonly modeled as Markovian streams; examples include words/sentences inferred f...
Julie Letchner, Christopher Re, Magdalena Balazins...
In this paper, we address the question of what kind of knowledge is generally transferable from unlabeled text. We suggest and analyze the semantic correlation of words as a gener...