Tensor network language model
arXiv:1710.10248
Abstract
We propose a new statistical model suitable for machine learning of systems with long distance correlations such as natural languages. The model is based on directed acyclic graph decorated by multi-linear tensor maps in the vertices and vector spaces in the edges, called tensor network. Such tensor networks have been previously employed for effective numerical computation of the renormalization group flow on the space of effective quantum field theories and lattice models of statistical mechanics. We provide explicit algebro-geometric analysis of the parameter moduli space for tree graphs, discuss model properties and applications such as statistical translation.
21 pages
References in corpus (12)
- Are biological systems poised at criticality?
- Classical simulation of quantum many-body systems with a tree tensor network
- Simulation of two-dimensional quantum systems using a tree tensor network that exploits the entropic area law
- Learning Thermodynamics with Boltzmann Machines
- Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
- Entropy and Long range correlations in literary English
- Entropy and Long range correlations in literary English
- An exact mapping between the Variational Renormalization Group and Deep Learning
- Perfect Sampling with Unitary Tensor Networks
- On the origin of long-range correlations in texts
- Wheeled PROPs, graph complexes and the master equation
- Practical variational tomography for critical 1D systems
Cited by in corpus (8)
- Differentiable Programming Tensor Networks
- lambeq: An Efficient High-Level Python Library for Quantum NLP
- Tensor network to learn the wavefunction of data
- Shortcut Matrix Product States and its applications
- Language Modeling with Reduced Densities
- Tensor Networks for Probabilistic Sequence Modeling
- Probabilistic Graphical Models and Tensor Networks: A Hybrid Framework
- At the Interface of Algebra and Statistics