A Convolutional Neural Network for Modelling Sentences

Abstract

The ability to accurately represent sentences is central to language understanding. We describe a convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) that we adopt for the semantic modelling of sentences. The network uses Dynamic k-Max Pooling, a global pooling operation over linear sequences. The network handles input sentences of varying length and induces a feature graph over the sentence that is capable of explicitly capturing short and long-range relations. The network does not rely on a parse tree and is easily applicable to any language. We test the DCNN in four experiments: small scale binary and multi-class sentiment prediction, six-way question classification and Twitter sentiment prediction by distant supervision. The network achieves excellent performance in the first three tasks and a greater than 25% error reduction in the last task with respect to the strongest baseline.

References in corpus (3)

• Improving neural networks by preventing co-adaptation of feature detectors
• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Mathematical Foundations for a Compositional Distributional Model of Meaning

Cited by in corpus (68)

• Convolutional Neural Networks for Sentence Classification
• Comparative Study of CNN and RNN for Natural Language Processing
• A Deep Relevance Matching Model for Ad-hoc Retrieval
• Deep Learning for Answer Sentence Selection
• Distilling Task-Specific Knowledge from BERT into Simple Neural Networks
• A Deep Reinforcement Learning Chatbot
• Representation learning for very short texts using weighted word embedding aggregation
• Adversarial Feature Matching for Text Generation
• Grammar Variational Autoencoder
• Evaluating Two-Stream CNN for Video Classification
• Combating Fake News: A Survey on Identification and Mitigation Techniques
• Do Convolutional Networks need to be Deep for Text Classification ?
• Applications of Online Deep Learning for Crisis Response Using Social Media Information
• Deconvolutional Paragraph Representation Learning
• Discriminative Neural Sentence Modeling by Tree-Based Convolution
• Learning text representation using recurrent convolutional neural network with highway layers
• Learning to Compose Words into Sentences with Reinforcement Learning
• Topic-based Evaluation for Conversational Bots
• EmoNets: Multimodal deep learning approaches for emotion recognition in video
• Rapid Classification of Crisis-Related Data on Social Networks using Convolutional Neural Networks
• PatchNet: Hierarchical Deep Learning-Based Stable Patch Identification for the Linux Kernel
• Deep Multi-Task Learning with Shared Memory
• Sales Forecast in E-commerce using Convolutional Neural Network
• Topic2Vec: Learning Distributed Representations of Topics
• Compositional Distributional Semantics with Long Short Term Memory
• Combining Convolution and Recursive Neural Networks for Sentiment Analysis
• 1D-Convolutional Capsule Network for Hyperspectral Image Classification
• Knowledge Graph Representation with Jointly Structural and Textual Encoding
• Enhancing Rumor Detection in Social Media Using Dynamic Propagation Structures
• Learning to Remember Translation History with a Continuous Cache
• $k$-Nearest Neighbor Augmented Neural Networks for Text Classification
• Deep Style Match for Complementary Recommendation
• UTCNN: a Deep Learning Model of Stance Classificationon on Social Media Text
• Deep Learning Based Cryptographic Primitive Classification
• Brain Intelligence: Go Beyond Artificial Intelligence
• Word Embeddings for Sentiment Analysis: A Comprehensive Empirical Survey
• Distributed Representations for Compositional Semantics
• DeepSQLi: Deep Semantic Learning for Testing SQL Injection
• Context-Dependent Translation Selection Using Convolutional Neural Network
• Dynamic Compositional Neural Networks over Tree Structure
• Hierarchical Question Answering for Long Documents
• A Context-Aware User-Item Representation Learning for Item Recommendation
• iCapsNets: Towards Interpretable Capsule Networks for Text Classification
• Article citation study: Context enhanced citation sentiment detection
• Targeted Advertising Based on Browsing History
• Exploring Different Dimensions of Attention for Uncertainty Detection
• A Language-independent and Compositional Model for Personality Trait Recognition from Short Texts
• Product-Aware Answer Generation in E-Commerce Question-Answering
• Sentiment Classification with Word Attention based on Weakly Supervised Learning with a Convolutional Neural Network
• Mapping distributional to model-theoretic semantic spaces: a baseline
• Neural Networks for Joint Sentence Classification in Medical Paper Abstracts
• Siamese convolutional networks based on phonetic features for cognate identification
• DialogAct2Vec: Towards End-to-End Dialogue Agent by Multi-Task Representation Learning
• Bringing Semantic Structures to User Intent Detection in Online Medical Queries
• Group Sparse CNNs for Question Classification with Answer Sets
• Paraphrase-Supervised Models of Compositionality
• A Weakly Supervised Approach to Train Temporal Relation Classifiers and Acquire Regular Event Pairs Simultaneously
• Job Detection in Twitter
• Drug cell line interaction prediction
• Text Classification with Lexicon from PreAttention Mechanism
• Mimicking Human Process: Text Representation via Latent Semantic Clustering for Classification
• Task-specific Word Identification from Short Texts Using a Convolutional Neural Network
• A Deep Learning-Based Approach for Measuring the Domain Similarity of Persian Texts
• Joint Learning of Distributed Representations for Images and Texts
• Emotion Correlation Mining Through Deep Learning Models on Natural Language Text
• Automatic Question-Answering Using A Deep Similarity Neural Network
• Constraint-free Natural Image Reconstruction from fMRI Signals Based on Convolutional Neural Network
• Learning Robust Representations of Text