Towards logical negation for compositional distributional semantics
This addresses a key limitation in compositional distributional semantics for natural language processing, but it is incremental as it provides initial steps rather than a full solution.
The paper tackled the lack of a logical negation operator in the categorical compositional distributional model of meaning by modeling negation as projection onto an orthogonal subspace, and demonstrated its performance in a sentence entailment task.
The categorical compositional distributional model of meaning gives the composition of words into phrases and sentences pride of place. However, it has so far lacked a model of logical negation. This paper gives some steps towards providing this operator, modelling it as a version of projection onto the subspace orthogonal to a word. We give a small demonstration of the operators performance in a sentence entailment task.