Quantum Language Model with Entanglement Embedding for Question Answering

TL;DR

This paper introduces a quantum language model with an entanglement embedding module that captures non-classical correlations in word sequences, leading to improved question answering performance and interpretability.

Contribution

It proposes a novel entanglement embedding module for quantum language models, explicitly modeling quantum entanglement in word sequences for enhanced QA performance.

Findings

QLM-EE outperforms classical neural networks and other QLMs on QA datasets.

The model's interpretability is enhanced by quantifying entanglement among words.

Strong quantum entanglement is observed within word sequences.

Abstract

Quantum Language Models (QLMs) in which words are modelled as quantum superposition of sememes have demonstrated a high level of model transparency and good post-hoc interpretability. Nevertheless, in the current literature word sequences are basically modelled as a classical mixture of word states, which cannot fully exploit the potential of a quantum probabilistic description. A full quantum model is yet to be developed to explicitly capture the non-classical correlations within the word sequences. We propose a neural network model with a novel Entanglement Embedding (EE) module, whose function is to transform the word sequences into entangled pure states of many-body quantum systems. Strong quantum entanglement, which is the central concept of quantum information and an indication of parallelized correlations among the words, is observed within the word sequences. Numerical experiments show that the proposed QLM with EE (QLM-EE) achieves superior performance compared with the classical deep neural network models and other QLMs on Question Answering (QA) datasets. In addition, the post-hoc interpretability of the model can be improved by quantizing the degree of entanglement among the words.