Convolutional Neural Network Architectures for Matching Natural Language Sentences

TL;DR

This paper introduces convolutional neural network models for sentence matching that effectively capture hierarchical structures and interaction patterns, demonstrating superior performance across various natural language matching tasks.

Contribution

It presents a novel CNN-based approach for sentence matching that is language-agnostic and adaptable to different tasks, improving upon existing models.

Findings

Models outperform competitors on multiple matching tasks.

Hierarchical sentence representations improve matching accuracy.

The approach is applicable across different languages and task types.

Abstract

Semantic matching is of central importance to many natural language tasks \cite{bordes2014semantic,RetrievalQA}. A successful matching algorithm needs to adequately model the internal structures of language objects and the interaction between them. As a step toward this goal, we propose convolutional neural network models for matching two sentences, by adapting the convolutional strategy in vision and speech. The proposed models not only nicely represent the hierarchical structures of sentences with their layer-by-layer composition and pooling, but also capture the rich matching patterns at different levels. Our models are rather generic, requiring no prior knowledge on language, and can hence be applied to matching tasks of different nature and in different languages. The empirical study on a variety of matching tasks demonstrates the efficacy of the proposed model on a variety of matching tasks and its superiority to competitor models.