understanding-ai
understanding-ai copied to clipboard
A Quantum Many-body Wave Function Inspired Language Modeling Approach
Abstract
- quantum probability theory
- quantum-inspired LMs have two limitations
- not taken into account interaction among the words with multiple meanings
- lacking theoretical foundation accounting for effective training parameters
-
QMWF
- can adopt the tensor product to model which interactions mong words
1. Introduction
- two LM approaches
- classical
- increase the number of parameters to be estimated for compound dependencies
- quantum inspired
- estimates density matrix
- encodes both single words and compound words (QLM)
- classical
-
QLM and NNQLM
- end-toend neural network structure
- are not modeled to complex interaction among words with multiple meanings
- no principled manner
- QWMF
- the wave function can model the interaction among many spinful particles
- convolutional neural network architecture can be mathematically derived in quantum-inspired language modeling approach
- outperforms quantum LM counterparts (QLM, NNQLM)
In this paper,
- propose Quantum Many-body Wave Function based Language Modeling approach
- able to represent complex interaction among words
- show fundamental connection between QMWF and CNN
- performance checking with QA datasets
2. Quantum Preliminaries
2.1. Basic notation and concepts
2.2. Quantum Many-body Wave Functions
3. Quantum many-body wave function inspired language modeling
3.1. Basic intuitions and architecture
- QMWF representation can model probability distribution of compound meanings
- depends on basis vectors
3.2. Language representation and projection via many-body wave function
- Local representation by product state
- Global representation for all possible compound meanings
3.3. Production realized by convolutional neural network
6. Experiments
My notes
- Can we think that QMWF is generalized version of attention mechanism?
- sum of a_i^2 is 1
- M = 1?