Convolutional Neural Network Architectures for Matching Natural Language Sentences

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.

References in corpus (2)

• Improving neural networks by preventing co-adaptation of feature detectors
• Natural Language Processing (almost) from Scratch

Cited by in corpus (21)

• Representation learning for very short texts using weighted word embedding aggregation
• Classifying Relations by Ranking with Convolutional Neural Networks
• Extraction of Salient Sentences from Labelled Documents
• Discriminative Neural Sentence Modeling by Tree-Based Convolution
• Encoding Source Language with Convolutional Neural Network for Machine Translation
• Self-Adaptive Hierarchical Sentence Model
• Learning text representation using recurrent convolutional neural network with highway layers
• Neural Information Retrieval: A Literature Review
• Deep Multi-Task Learning with Shared Memory
• Syntax-based Deep Matching of Short Texts
• Answer Sequence Learning with Neural Networks for Answer Selection in Community Question Answering
• Local Translation Prediction with Global Sentence Representation
• Learning to Match Using Local and Distributed Representations of Text for Web Search
• $gen$CNN: A Convolutional Architecture for Word Sequence Prediction
• Context-Dependent Translation Selection Using Convolutional Neural Network
• Toward a Deep Neural Approach for Knowledge-Based IR
• Learning Semantically Coherent and Reusable Kernels in Convolution Neural Nets for Sentence Classification
• Neural Network Based Next-Song Recommendation
• Learning Word Embeddings from Intrinsic and Extrinsic Views
• Luandri: a Clean Lua Interface to the Indri Search Engine
• Character-level Deep Conflation for Business Data Analytics