Quantum Inspired Word Representation and Computation
This work addresses the limitation of single-vector word representations in natural language processing, offering a novel approach for researchers in computational linguistics, though it is incremental in advancing representation methods.
The paper tackles the problem of representing multiple aspects of word meaning by proposing a quantum-inspired density matrix representation, which effectively captures different aspects while maintaining reliability comparable to vector representations, and achieves consistent improvement on word analogy tasks.
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.