CNM: An Interpretable Complex-valued Network for Matching

TL;DR

This paper introduces CNM, a complex-valued neural network inspired by quantum physics principles, designed for semantic matching in language understanding, offering interpretability and competitive performance on QA benchmarks.

Contribution

It presents a novel complex-valued network framework that models linguistic units in a quantum-inspired vector space, enhancing interpretability and performance in semantic matching tasks.

Findings

Achieves comparable results to CNN and RNN baselines on QA datasets.

Provides interpretable physical meanings for complex-valued components.

Unifies linguistic units in a quantum-inspired mathematical framework.

Abstract

This paper seeks to model human language by the mathematical framework of quantum physics. With the well-designed mathematical formulations in quantum physics, this framework unifies different linguistic units in a single complex-valued vector space, e.g. words as particles in quantum states and sentences as mixed systems. A complex-valued network is built to implement this framework for semantic matching. With well-constrained complex-valued components, the network admits interpretations to explicit physical meanings. The proposed complex-valued network for matching (CNM) achieves comparable performances to strong CNN and RNN baselines on two benchmarking question answering (QA) datasets.