“Not not bad” is not “bad”: A distributional account of negation

By Karl Moritz Hermann, Edward Grefenstette, Phil Blunsom. 2013

48 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computational Linguistics & Semantics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Linguistics & Semantics

Citations in the corpus

Probing for semantic evidence of composition by means of simple classification tasks (2016, methodology): “knowledged in NLP, in particular for applications such as sentiment analysis (Blunsom et al., 2013; Iyyer et al., 2015).”
Recursive Neural Networks Can Learn Logical Semantics (2014, background): “However, it remains an open question whether any such fully learned model can achieve the kind of high-fidelity distributed representations proposed in recent algebraic work on vector space modeling (Coecke et al., 2011; Grefenstette, 2013; Hermann et al., 2013; Rocktäschel et al., 2014), and whethe”
Formal Distributional Semantics: Introduction to the Special Issue (2016, background): “Other phenomena such as negation and relative pronouns have started receiving treatment: In Hermann, Grefenstette, and Blunsom (2013), negation is deﬁned as the distributional complement of a term in a particular domain; similarly, Kruszewski et al. (this issue) show that distributional…”