DeepAI AI Chat
Log In Sign Up

Quantum Inspired Word Representation and Computation

by   Shen Li, et al.
Beijing Normal University

Word meaning has different aspects, while the existing word representation "compresses" these aspects into a single vector, and it needs further analysis to recover the information in different dimensions. Inspired by quantum probability, we represent words as density matrices, which are inherently capable of representing mixed states. The experiment shows that the density matrix representation can effectively capture different aspects of word meaning while maintaining comparable reliability with the vector representation. Furthermore, we propose a novel method to combine the coherent summation and incoherent summation in the computation of both vectors and density matrices. It achieves consistent improvement on word analogy task.


page 1

page 2

page 3

page 4


Modelling Lexical Ambiguity with Density Matrices

Words can have multiple senses. Compositional distributional models of m...

Quantum-inspired Complex Word Embedding

A challenging task for word embeddings is to capture the emergent meanin...

Context-aware Sentiment Word Identification: sentiword2vec

Traditional sentiment analysis often uses sentiment dictionary to extrac...

Meaning updating of density matrices

The DisCoCat model of natural language meaning assigns meaning to a sent...

Dual Density Operators and Natural Language Meaning

Density operators allow for representing ambiguity about a vector repres...

Representing Sets as Summed Semantic Vectors

Representing meaning in the form of high dimensional vectors is a common...