Bell States and Negative Sentences in the Distributed Model of Meaning

Abstract

We use Bell states to provide compositional distributed meaning for negative sentences of English. The lexical meaning of each word of the sentence is a context vector obtained within the distributed model of meaning. The meaning of the sentence lives within the tensor space of the vector spaces of the words. Mathematically speaking, the meaning of a sentence is the image of a quantizing functor from the compact closed category that models the grammatical structure of the sentence (using Lambek Pregroups) to the compact closed category of finite dimensional vector spaces where the lexical meaning of the words are modeled. The meaning is computed via composing eta and epsilon maps that create Bell states and do substitution and as such allow the information to flow among the words within the sentence.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 31 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.