Convolutional Neural Network Architectures for Matching Natural Language Sentences

TLDR

Semantic matching is central to many NLP tasks and requires modeling the internal structures of language objects and their interactions. We propose convolutional neural network models that adapt the convolutional strategy from vision and speech to match two sentences. These models hierarchically compose and pool sentence representations, capturing rich matching patterns at multiple levels, and are generic enough to apply across languages and tasks without prior linguistic knowledge. Across a variety of matching tasks, the proposed models outperform competitor approaches, demonstrating superior efficacy.

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.