Convolutional Neural Networks for Sentence Classification
Not on the map. Why?
Abstract (arXiv)
We report on a series of experiments with convolutional neural networks (CNN) trained on top of pre-trained word vectors for sentence-level classification tasks. We show that a simple CNN with little hyperparameter tuning and static vectors achieves excellent results on multiple benchmarks. Learning task-specific vectors through fine-tuning offers further gains in performance. We additionally propose a simple modification to the architecture to allow for the use of both task-specific and static vectors. The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification.
Key facts. Cited by 1,127 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Aug 2014.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2018: 3; 2019: 1; 2020: 1; 2021: 400; 2022: 251; 2023: 177; 2024: 133; 2025: 97; 2026: 64.
1,127 papers.
Sort:
By area:
- 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
- 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 744
- 2023Larger language models do in-context learning differentlycited by 394
- 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 365
- 2021Pre-Trained Models: Past, Present and Futurecited by 319
- 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 279
- 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 187
- 2022Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Modelscited by 180
- 2022Mega: Moving Average Equipped Gated Attentioncited by 179
- 2022A Review on Language Models as Knowledge Basescited by 157
- 2022Learning on Large-scale Text-attributed Graphs via Variational Inferencecited by 155
- 2021DriveGAN: Towards a Controllable High-Quality Neural Simulationcited by 125
38 more
- 2021Advances and Challenges in Conversational Recommender Systems: A Surveycited by 118
- 2023A Comprehensive Survey of Dataset Distillationcited by 115
- 2021COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted Listcited by 113
- 2021Dive into Deep Learningcited by 111
- 2021BERT: A Review of Applications in Natural Language Processing and Understandingcited by 109
- 2022Long Time No See! Open-Domain Conversation with Long-Term Persona Memorycited by 108
- 2023Text Classification via Large Language Modelscited by 106
- 2021Achieving Forgetting Prevention and Knowledge Transfer in Continual Learningcited by 91
- 2021Unified Named Entity Recognition as Word-Word Relation Classificationcited by 90
- 2023SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networkscited by 88
- 2021HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrievalcited by 87
- 2021Pre-trained Language Models in Biomedical Domain: A Systematic Surveycited by 87
- 2023A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4cited by 81
- 2021ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanationcited by 78
- 2021Differentiable Learning Under Triagecited by 76
- 2022How would Stance Detection Techniques Evolve after the Launch of ChatGPT?cited by 76
- 2022I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defencescited by 75
- 2021BertGCN: Transductive Text Classification by Combining GCN and BERTcited by 74
- 2021DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversationscited by 71
- 2022Mapping global dynamics of benchmark creation and saturation in artificial intelligencecited by 71
- 2022Calibrated Learning to Defer with One-vs-All Classifierscited by 69
- 2022MDFEND: Multi-domain Fake News Detectioncited by 68
- 2021AEDA: An Easier Data Augmentation Technique for Text Classificationcited by 67
- 2021Triggerless Backdoor Attack for NLP Tasks with Clean Labelscited by 66
- 2022When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learningcited by 65
- 2022Black-box Dataset Ownership Verification via Backdoor Watermarkingcited by 65
- 2021Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solutioncited by 64
- 2021Multi-Modal 3D Object Detection in Autonomous Driving: a Surveycited by 63
- 2021SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representationcited by 63
- 2018Multi-Source Domain Adaptation with Mixture of Expertscited by 62
- 2022A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challengescited by 61
- 2021T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classificationcited by 60
- 2021Revisiting Uncertainty-based Query Strategies for Active Learning with Transformerscited by 60
- 2022Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensemblescited by 60
- 2021A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendationcited by 59
- 2018Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learningcited by 57
- 2022Log-based Anomaly Detection with Deep Learning: How Far Are We?cited by 57
- 2023Deception Detection from Linguistic and Physiological Data Streams Using Bimodal Convolutional Neural Networkscited by 56
50 most cited of 1,127 All 1,127 (JSON)
- 2026ProtoSemImage: Image-Valued Prototypes with Deformable Row Alignment for Interpretable Document Classification8 Oct 2026
- 2026Does Neural Complexity Improve Health Misinformation Detection? A Leakage-Controlled Cross-Corpus Benchmark3 Oct 2026
- 2026Representable but Unlearned: Encoding Rank and the Interaction-Prediction Floor28 Sep 2026
- 2026GCUL: Ambiguity Identification in Text Emotion Classification via Cluster-Guided Learning24 Sep 2026
- 2026Perplexity Predicts Protection: Choosing Pretrained Backbones for Worst-Client Fairness in Federated Parameter-Efficient Fine-Tuning20 Sep 2026
- 2026SENTINEL: A Multi-Pathway Architecture for Detecting Living-Off-the-Land APT Attacks on Windows Command Lines13 Sep 2026
- 2026Dynamic Gated Cross-Modal Fusion with Sarcastic-aware Contrastive Regularization for Multimodal Sarcasm Detection20 Aug 2026
- 2026Discovering Persistent Behavioural Patterns for Interpretable Blockchain Forensics13 Aug 2026
- 2026Dual-Model Sentiment Analysis of Consumer Reviews in the Retail Coffee Sector Using Machine Learning and Deep Learning Approaches12 Aug 2026
- 2026pico-type: A 1.5M-Parameter Byte-Level Multi-Head Content Classifier31 Jul 2026
- 2026Evaluation of Adversarial Robustness in Arabic Language Models28 Jul 2026
- 2026FacetCRS: Multi-Faceted Preference Learning for Pricking Filter Bubbles in Conversational Recommender System24 Jul 2026
38 more
- 2026Test Case Prioritization for DNNs via Neural Collapse Instability22 Jul 2026
- 2026Mitigating Matthew Effect: Multi-Hypergraph Boosted Multi-Interest Self-Supervised Learning for Conversational Recommendation21 Jul 2026
- 2026HyCoRec: Hypergraph-Enhanced Multi-Preference Learning for Alleviating Matthew Effect in Conversational Recommendation20 Jul 2026
- 2026Automatic Thematic Indexing of Large Literary Corpora: A Machine Learning Approach to Voltaire's Complete Works10 Jul 2026
- 2026Drift Happens: An Empirical Study of Neural Architecture Robustness to Temporal Distribution Shift7 Jul 2026
- 2026Hybrid quantum-classical neural network for sentiment analysis2 Jul 2026
- 2026Vulnerability of Natural Language Classifiers to Evolutionary Generated Adversarial Text25 Jun 2026
- 2026Insulin4RL: Real-Time Insulin Management in the Intensive Care Unit for Offline Reinforcement Learning17 Jun 2026
- 2026TAKE: Trajectory-Aware Knowledge Estimation for Text Dataset Distillation13 Jun 2026
- 2026S-GBT: Smooth Growth Bound Tensor for Certified Robustness Against Word Substitution Attacks in NLP11 Jun 2026
- 2026An Improved CNN-LSTM Based Intrusion Detection System for IoT Networks4 Jun 2026
- 2026Seq103: A Unified Neuroevolution Framework for Compact Sequence Architecture Discovery3 Jun 2026
- 2026Dynamic Short Convolutions Improve Transformers2 Jun 2026
- 2026SEP-Attack: A Simple and Effective Paradigm for Transfer-Based Textual Adversarial Attack24 May 2026
- 2026Advancing Direct Training for Spiking Neural Networks with Circulate-Firing Neurons and Learnable Gradients14 May 2026
- 2026TokAlign++: Advancing Vocabulary Adaptation via Better Token Alignment13 May 2026
- 2026DRIFT: Drift-Resilient Invariant-Feature Transformer for DGA Detection11 May 2026
- 2026FedVSSAM: Mitigating Flatness Incompatibility in Sharpness-Aware Federated Learning9 May 2026
- 2026When More Parameters Hurt: Foundation Model Priors Amplify Worst-Client Disparity Under Extreme Federated Heterogeneity9 May 2026
- 2026Max-pooling Network Revisited: Analyzing the Role of Semantic Probability in Multiple Instance Learning for Hallucination Detection9 May 2026
- 2026Hybrid TF--IDF Logistic Regression and MLP Neural Baseline for Indonesian Three-Class Sentiment Analysis on Social Media Text8 May 2026
- 2026A Comparative Study of PyCaret AutoML and CNN-BiLSTM for Binary Hate Speech Detection in Indonesian Twitter6 May 2026
- 2026LBA: Textual Hard-Label Adversarial Attack under Low Query Budgets5 May 2026
- 2026Natural Language Processing: A Comprehensive Practical Guide from Tokenisation to RLHF5 May 2026
- 2026PoQ-Judge: A Multi-Architecture Evaluation Framework for Cost-Aware Proof-of-Quality in Decentralized LLM Inference20 Apr 2026
- 2026Evolution-Inspired Sample Competition for Deep Neural Network Optimization14 Apr 2026
- 2026Dynamic Adaptive Attention and Supervised Contrastive Learning: A Novel Hybrid Framework for Text Sentiment Classification12 Apr 2026
- 2026A GAN and LLM-Driven Data Augmentation Framework for Dynamic Linguistic Pattern Modeling in Chinese Sarcasm Detection9 Apr 2026
- 2026Kathleen: Oscillator-Based Byte-Level Text Classification Without Tokenization or Attention9 Apr 2026
- 2026iTAG: Inverse Design for Natural Text Generation with Accurate Causal Graph Annotations8 Apr 2026
- 2026Embedding Enhancement via Fine-Tuned Language Models for Learner-Item Cognitive Modeling5 Apr 2026
- 2026AI Appeals Processor: A Deep Learning Approach to Automated Classification of Citizen Appeals in Government Services4 Apr 2026
- 2026Dual-branch Graph Domain Adaptation for Cross-scenario Multi-modal Emotion Recognition27 Mar 2026
- 2026Semi-Supervised Learning with Balanced Deep Representation Distributions22 Mar 2026
- 2026Automatic detection of Gen-AI texts: A comparative framework of neural models19 Mar 2026
- 2026Detecting the Machine: A Comprehensive Benchmark of AI-Generated Text Detectors Across Architectures, Domains, and Adversarial Conditions18 Mar 2026
- 2026VERDICT: Verifiable Evolving Reasoning with Directive-Informed Collegial Teams for Legal Judgment Prediction13 Mar 2026
- 2026An Automatic Text Classification Method Based on Hierarchical Taxonomies, Neural Networks and Document Embedding: The NETHIC Tool12 Mar 2026
50 newest of 1,127 All 1,127 (JSON)
- 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 187
- 2022Uni-Retriever: Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Searchcited by 17
- 2022Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddingscited by 17
- 2023SpikeBERT: A Language Spikformer Learned from BERT with Knowledge Distillationcited by 17
- 2023FedACK: Federated Adversarial Contrastive Knowledge Distillation for Cross-Lingual and Cross-Model Social Bot Detectioncited by 12
- 2021Self-Training with Differentiable Teachercited by 7
- 2022Which Student is Best? A Comprehensive Knowledge Distillation Exam for Task-Specific BERT Modelscited by 5
- 2023DisCo: Distilled Student Models Co-training for Semi-supervised Text Miningcited by 4
- 2024MIKO: Multimodal Intention Knowledge Distillation from Large Language Models for Social-Media Commonsense Discoverycited by 3
- 2023Dual-Teacher De-biasing Distillation Framework for Multi-domain Fake News Detectioncited by 2
- 2023Explainability-Driven Leaf Disease Classification Using Adversarial Training and Knowledge Distillationcited by 1
- 2024MIKO: Multimodal Intention Knowledge Distillation from Large Language Models for Social-Media Commonsense Discovery28 Feb 2024
- 2023Explainability-Driven Leaf Disease Classification Using Adversarial Training and Knowledge Distillation30 Dec 2023
- 2023Dual-Teacher De-biasing Distillation Framework for Multi-domain Fake News Detection2 Dec 2023
- 2023SpikeBERT: A Language Spikformer Learned from BERT with Knowledge Distillation29 Aug 2023
- 2023DisCo: Distilled Student Models Co-training for Semi-supervised Text Mining20 May 2023
- 2023FedACK: Federated Adversarial Contrastive Knowledge Distillation for Cross-Lingual and Cross-Model Social Bot Detection10 Mar 2023
- 2022Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings1 Apr 2022
- 2022Uni-Retriever: Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Search13 Feb 2022
- 2022Which Student is Best? A Comprehensive Knowledge Distillation Exam for Task-Specific BERT Models3 Jan 2022
- 2021Self-Training with Differentiable Teacher15 Sep 2021
- 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillation30 Aug 2021
- 2021Triggerless Backdoor Attack for NLP Tasks with Clean Labelscited by 66
- 2021T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classificationcited by 60
- 2026Building Production-Ready Probes For Geminicited by 47
- 2023Defending against Insertion-based Textual Backdoor Attacks via Attributioncited by 25
- 2021BFClass: A Backdoor-free Text Classification Frameworkcited by 19
- 2022Poison Attack and Defense on Deep Source Code Processing Modelscited by 11
- 2022Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregationcited by 8
- 2021On the privacy-utility trade-off in differentially private hierarchical text classificationcited by 4
- 2023Adversarial Data Poisoning for Fake News Detection: How to Make a Model Misclassify a Target News without Modifying Itcited by 1
- 2025Estimating Model-Level Membership Inference Vulnerability Without Reference Modelscited by 1
- 2026Building Production-Ready Probes For Gemini16 Jan 2026
- 2025Estimating Model-Level Membership Inference Vulnerability Without Reference Models22 Oct 2025
- 2023Adversarial Data Poisoning for Fake News Detection: How to Make a Model Misclassify a Target News without Modifying It23 Dec 2023
- 2023Defending against Insertion-based Textual Backdoor Attacks via Attribution3 May 2023
- 2022Poison Attack and Defense on Deep Source Code Processing Models31 Oct 2022
- 2022Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation13 Oct 2022
- 2021Triggerless Backdoor Attack for NLP Tasks with Clean Labels15 Nov 2021
- 2021BFClass: A Backdoor-free Text Classification Framework22 Sep 2021
- 2021T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification7 Mar 2021
- 2021On the privacy-utility trade-off in differentially private hierarchical text classification4 Mar 2021
- 2018Multi-Source Domain Adaptation with Mixture of Expertscited by 62
- 2024MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuningcited by 19
- 2023Improved Training of Mixture-of-Experts Language GANscited by 7
- 2018Dropout Regularization in Hierarchical Mixture of Expertscited by 6
- 2025MHSNet:An MoE-based Hierarchical Semantic Representation Network for Accurate Duplicate Resume Detection with Large Language Modelcited by 0
- 2025MHSNet:An MoE-based Hierarchical Semantic Representation Network for Accurate Duplicate Resume Detection with Large Language Model19 Aug 2025
- 2024MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning23 Oct 2024
- 2023Improved Training of Mixture-of-Experts Language GANs23 Feb 2023
- 2018Dropout Regularization in Hierarchical Mixture of Experts25 Dec 2018
- 2018Multi-Source Domain Adaptation with Mixture of Experts7 Sep 2018
- 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 279
- 2024A Survey on Vision-Language-Action Models for Embodied AI23 May 2024
- 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
- 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 744
- 2023Larger language models do in-context learning differentlycited by 394
- 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 365
- 2021Pre-Trained Models: Past, Present and Futurecited by 319
- 2022Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Modelscited by 180
- 2022Mega: Moving Average Equipped Gated Attentioncited by 179
- 2022A Review on Language Models as Knowledge Basescited by 157
- 2022Learning on Large-scale Text-attributed Graphs via Variational Inferencecited by 155
- 2021DriveGAN: Towards a Controllable High-Quality Neural Simulationcited by 125
- 2021Advances and Challenges in Conversational Recommender Systems: A Surveycited by 118
- 2023A Comprehensive Survey of Dataset Distillationcited by 115
12 most cited of 1,082 All 1,082 (JSON)
- 2026ProtoSemImage: Image-Valued Prototypes with Deformable Row Alignment for Interpretable Document Classification8 Oct 2026
- 2026Does Neural Complexity Improve Health Misinformation Detection? A Leakage-Controlled Cross-Corpus Benchmark3 Oct 2026
- 2026Representable but Unlearned: Encoding Rank and the Interaction-Prediction Floor28 Sep 2026
- 2026GCUL: Ambiguity Identification in Text Emotion Classification via Cluster-Guided Learning24 Sep 2026
- 2026Perplexity Predicts Protection: Choosing Pretrained Backbones for Worst-Client Fairness in Federated Parameter-Efficient Fine-Tuning20 Sep 2026
- 2026SENTINEL: A Multi-Pathway Architecture for Detecting Living-Off-the-Land APT Attacks on Windows Command Lines13 Sep 2026
- 2026Dynamic Gated Cross-Modal Fusion with Sarcastic-aware Contrastive Regularization for Multimodal Sarcasm Detection20 Aug 2026
- 2026Discovering Persistent Behavioural Patterns for Interpretable Blockchain Forensics13 Aug 2026
- 2026Dual-Model Sentiment Analysis of Consumer Reviews in the Retail Coffee Sector Using Machine Learning and Deep Learning Approaches12 Aug 2026
- 2026pico-type: A 1.5M-Parameter Byte-Level Multi-Head Content Classifier31 Jul 2026
- 2026Evaluation of Adversarial Robustness in Arabic Language Models28 Jul 2026
- 2026FacetCRS: Multi-Faceted Preference Learning for Pricking Filter Bubbles in Conversational Recommender System24 Jul 2026
12 newest of 1,082 All 1,082 (JSON)