A Quantum Many-body Wave Function Inspired Language Modeling Approach

TL;DR

This paper introduces a quantum many-body wave function inspired language model that models complex word interactions and integrates CNNs, showing improved performance on question answering datasets over existing quantum-inspired and CNN-based models.

Contribution

It proposes a novel QMWF-inspired language modeling approach that captures multi-meaning word interactions and provides a theoretical foundation for CNN integration.

Findings

Outperforms state-of-the-art quantum-inspired LMs and CNN-based methods on QA datasets.

Models interactions among words using tensor product.

Reveals the necessity of CNNs in QMWF language modeling.

Abstract

The recently proposed quantum language model (QLM) aimed at a principled approach to modeling term dependency by applying the quantum probability theory. The latest development for a more effective QLM has adopted word embeddings as a kind of global dependency information and integrated the quantum-inspired idea in a neural network architecture. While these quantum-inspired LMs are theoretically more general and also practically effective, they have two major limitations. First, they have not taken into account the interaction among words with multiple meanings, which is common and important in understanding natural language text. Second, the integration of the quantum-inspired LM with the neural network was mainly for effective training of parameters, yet lacking a theoretical foundation accounting for such integration. To address these two issues, in this paper, we propose a Quantum Many-body Wave Function (QMWF) inspired language modeling approach. The QMWF inspired LM can adopt the tensor product to model the aforesaid interaction among words. It also enables us to reveal the inherent necessity of using Convolutional Neural Network (CNN) in QMWF language modeling. Furthermore, our approach delivers a simple algorithm to represent and match text/sentence pairs. Systematic evaluation shows the effectiveness of the proposed QMWF-LM algorithm, in comparison with the state of the art quantum-inspired LMs and a couple of CNN-based methods, on three typical Question Answering (QA) datasets.