"Not not bad" is not "bad": A distributional account of negation
This addresses a key limitation in compositional semantics for NLP researchers, though it appears incremental as it builds on existing distributional models.
The paper tackled the inability of current distributional models to capture logical operations like negation, proposing a tripartite formulation for continuous vector space semantics to develop a formal compositional notion of negation.
With the increasing empirical success of distributional models of compositional semantics, it is timely to consider the types of textual logic that such models are capable of capturing. In this paper, we address shortcomings in the ability of current models to capture logical operations such as negation. As a solution we propose a tripartite formulation for a continuous vector space representation of semantics and subsequently use this representation to develop a formal compositional notion of negation within such models.