Convolutional Neural Network Architectures for Matching Natural Language Sentences
This work addresses semantic matching for natural language processing tasks, offering a generic method applicable across different languages and task types, though it is incremental as it adapts existing convolutional strategies.
The authors tackled the problem of semantic matching between sentences by proposing convolutional neural network models, which achieved superior performance over competitor models on a variety of matching tasks.
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.