Convolutional Neural Networks for Sentence Classification

Abstract

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.

To appear in EMNLP 2014

References in corpus (4)

• Improving neural networks by preventing co-adaptation of feature detectors
• ADADELTA: An Adaptive Learning Rate Method
• Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales
• A Convolutional Neural Network for Modelling Sentences

Cited by in corpus (389)

• Axiomatic Attribution for Deep Networks
• Deep Learning for Anomaly Detection: A Survey
• A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
• Style Transfer from Non-Parallel Text by Cross-Alignment
• Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
• FPGA-based Accelerators of Deep Learning Networks for Learning and Classification: A Review
• Semi-supervised Sequence Learning
• An efficient framework for learning sentence representations
• Learning to Generate Reviews and Discovering Sentiment
• SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
• A Survey on Natural Language Processing for Fake News Detection
• Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey
• CodeBERT: A Pre-Trained Model for Programming and Natural Languages
• An Analysis of Hierarchical Text Classification Using Word Embeddings
• Hierarchical Multiscale Recurrent Neural Networks
• A Benchmark Study of Machine Learning Models for Online Fake News Detection
• TI-CNN: Convolutional Neural Networks for Fake News Detection
• Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
• Natural Language Inference over Interaction Space
• Natural Language Processing Advancements By Deep Learning: A Survey
• DKN: Deep Knowledge-Aware Network for News Recommendation
• Long Short-Term Memory-Networks for Machine Reading
• Patient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record
• Efficient Character-level Document Classification by Combining Convolution and Recurrent Layers
• On weight initialization in deep neural networks
• Deep Learning and Its Applications to Machine Health Monitoring: A Survey
• dna2vec: Consistent vector representations of variable-length k-mers
• Learn to Combine Modalities in Multimodal Deep Learning
• Look Before You Leap: Detecting Phishing Web Pages by Exploiting Raw URL And HTML Characteristics
• A Deep Network Model for Paraphrase Detection in Short Text Messages
• Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks
• DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
• Revisiting Binary Code Similarity Analysis using Interpretable Feature Engineering and Lessons Learned
• Learning to Explain: An Information-Theoretic Perspective on Model Interpretation
• ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation
• Hierarchical Text Classification with Reinforced Label Assignment
• Sequence Learning with RNNs for Medical Concept Normalization in User-Generated Texts
• MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization
• Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment
• Universal Joint Feature Extraction for P300 EEG Classification using Multi-task Autoencoder
• Improving Twitter Sentiment Classification via Multi-Level Sentiment-Enriched Word Embeddings
• Improved Deep Learning Baselines for Ubuntu Corpus Dialogs
• STRIP: A Defence Against Trojan Attacks on Deep Neural Networks
• Joint Deep Modeling of Users and Items Using Reviews for Recommendation
• Neural Models for Information Retrieval
• EmotionLines: An Emotion Corpus of Multi-Party Conversations
• Does the Magic of BERT Apply to Medical Code Assignment? A Quantitative Study
• Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network
• A Generalization of Convolutional Neural Networks to Graph-Structured Data
• Multi-Modal Emotion recognition on IEMOCAP Dataset using Deep Learning
• Data driven approximation of parametrized PDEs by Reduced Basis and Neural Networks
• Automatic Rule Extraction from Long Short Term Memory Networks
• Discriminative Neural Sentence Modeling by Tree-Based Convolution
• Text Classification using Capsules
• Interpretation of Prediction Models Using the Input Gradient
• Improving the Accuracy of Pre-trained Word Embeddings for Sentiment Analysis
• Current Limitations in Cyberbullying Detection: on Evaluation Criteria, Reproducibility, and Data Scarcity
• Analysis of Railway Accidents' Narratives Using Deep Learning
• A Survey on Transfer Learning in Natural Language Processing
• Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction
• GLAC Net: GLocal Attention Cascading Networks for Multi-image Cued Story Generation
• Learning to Decode for Future Success
• BertGCN: Transductive Text Classification by Combining GCN and BERT
• Deep EHR: Chronic Disease Prediction Using Medical Notes
• Unsupervised Text Style Transfer using Language Models as Discriminators
• Neural Sentence Embedding using Only In-domain Sentences for Out-of-domain Sentence Detection in Dialog Systems
• Joint Embedding of Words and Labels for Text Classification
• Neural Information Retrieval: A Literature Review
• Attend and Diagnose: Clinical Time Series Analysis using Attention Models
• Leveraging Deep Graph-Based Text Representation for Sentiment Polarity Applications
• Explaining Explanations: Axiomatic Feature Interactions for Deep Networks
• Neural Models for Sequence Chunking
• BERT-based Financial Sentiment Index and LSTM-based Stock Return Predictability
• A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learning
• BiERU: Bidirectional Emotional Recurrent Unit for Conversational Sentiment Analysis
• Deep Active Learning for Named Entity Recognition
• EmotionX-IDEA: Emotion BERT -- an Affectional Model for Conversation
• Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering
• Deep-Sentiment: Sentiment Analysis Using Ensemble of CNN and Bi-LSTM Models
• Word Embedding Perturbation for Sentence Classification
• Deep Multi-Task Learning with Shared Memory
• Task-Oriented Query Reformulation with Reinforcement Learning
• Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications
• Visualizing and Understanding Curriculum Learning for Long Short-Term Memory Networks
• Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks
• Word Embeddings and Their Use In Sentence Classification Tasks
• Machine Reading Comprehension: a Literature Review
• Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good
• Neural Compatibility Modeling with Attentive Knowledge Distillation
• Deepr: A Convolutional Net for Medical Records
• Enhance word representation for out-of-vocabulary on Ubuntu dialogue corpus
• Confusion2Vec: Towards Enriching Vector Space Word Representations with Representational Ambiguities
• Sentence Pair Scoring: Towards Unified Framework for Text Comprehension
• A Neural Topic-Attention Model for Medical Term Abbreviation Disambiguation
• Interpreting Deep Learning Models in Natural Language Processing: A Review
• A Survey on Knowledge Graph-Based Recommender Systems
• Interpretable Multi-Modal Hate Speech Detection
• MGNC-CNN: A Simple Approach to Exploiting Multiple Word Embeddings for Sentence Classification
• DOC: Deep Open Classification of Text Documents
• Learning Loss Functions for Semi-supervised Learning via Discriminative Adversarial Networks
• AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search
• Consistent Estimators for Learning to Defer to an Expert
• Rationale-Augmented Convolutional Neural Networks for Text Classification
• CrisisBERT: a Robust Transformer for Crisis Classification and Contextual Crisis Embedding
• Experimental Evaluation of Deep Learning models for Marathi Text Classification
• Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification
• Misogynistic Tweet Detection: Modelling CNN with Small Datasets
• No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling
• Lexicon Integrated CNN Models with Attention for Sentiment Analysis
• A Large-Scale Study of the Twitter Follower Network to Characterize the Spread of Prescription Drug Abuse Tweets
• Joint Online Spoken Language Understanding and Language Modeling with Recurrent Neural Networks
• Fast Neural Network Verification via Shadow Prices
• Recurrent Neural Network-Based Sentence Encoder with Gated Attention for Natural Language Inference
• Overview of CAIL2018: Legal Judgment Prediction Competition
• Transformer to CNN: Label-scarce distillation for efficient text classification
• Sentiment Classification in Swahili Language Using Multilingual BERT
• Searching for Effective Neural Extractive Summarization: What Works and What's Next
• Highrisk Prediction from Electronic Medical Records via Deep Attention Networks
• Few-shot Learning with Meta Metric Learners
• Combining Convolution and Recursive Neural Networks for Sentiment Analysis
• TS-CNN: Text Steganalysis from Semantic Space Based on Convolutional Neural Network
• KATE: K-Competitive Autoencoder for Text
• Comparing Rule-Based and Deep Learning Models for Patient Phenotyping
• Ranking Distillation: Learning Compact Ranking Models With High Performance for Recommender System
• Multitask Learning for Emotion and Personality Detection
• Multi-Modal 3D Object Detection in Autonomous Driving: a Survey
• SPI: Automated Identification of Security Patches via Commits
• Convolutional RNN: an Enhanced Model for Extracting Features from Sequential Data
• Multimodal Attribute Extraction
• Multichannel CNN with Attention for Text Classification
• Deep Learning and Word Embeddings for Tweet Classification for Crisis Response
• Character-level Convolutional Network for Text Classification Applied to Chinese Corpus
• Optimizing Gross Merchandise Volume via DNN-MAB Dynamic Ranking Paradigm
• Gated Recurrent Neural Network Approach for Multilabel Emotion Detection in Microblogs
• Integrating Semantic Knowledge to Tackle Zero-shot Text Classification
• HDF: Hybrid Deep Features for Scene Image Representation
• Word Mover's Embedding: From Word2Vec to Document Embedding
• Multi-Label Learning from Medical Plain Text with Convolutional Residual Models
• Single-Pass PCA of Large High-Dimensional Data
• Recognizing Explicit and Implicit Hate Speech Using a Weakly Supervised Two-path Bootstrapping Approach
• MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure Prediction
• Learning beyond datasets: Knowledge Graph Augmented Neural Networks for Natural language Processing
• Quantifying Uncertainties in Natural Language Processing Tasks
• Be More with Less: Hypergraph Attention Networks for Inductive Text Classification
• Zero-shot User Intent Detection via Capsule Neural Networks
• DeepCCI: End-to-end Deep Learning for Chemical-Chemical Interaction Prediction
• Generating lyrics with variational autoencoder and multi-modal artist embeddings
• Dirichlet Variational Autoencoder for Text Modeling
• Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding
• From Independent Prediction to Re-ordered Prediction: Integrating Relative Position and Global Label Information to Emotion Cause Identification
• Lyrics-Based Music Genre Classification Using a Hierarchical Attention Network
• Disentangled Variational Auto-Encoder for Semi-supervised Learning
• A Data-driven Neural Network Architecture for Sentiment Analysis
• Conditional BERT Contextual Augmentation
• Syntactic Recurrent Neural Network for Authorship Attribution
• Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability
• Sentence Boundary Detection for French with Subword-Level Information Vectors and Convolutional Neural Networks
• Neural Contextual Conversation Learning with Labeled Question-Answering Pairs
• Alquist 2.0: Alexa Prize Socialbot Based on Sub-Dialogue Models
• $k$-Nearest Neighbor Augmented Neural Networks for Text Classification
• Deep Multimodal Learning for Emotion Recognition in Spoken Language
• No Need to Pay Attention: Simple Recurrent Neural Networks Work! (for Answering "Simple" Questions)
• Active Discriminative Text Representation Learning
• Modeling Long-Range Context for Concurrent Dialogue Acts Recognition
• Recursive Graphical Neural Networks for Text Classification
• Convolutional neural network compression for natural language processing
• Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations
• Elephant in the Room: An Evaluation Framework for Assessing Adversarial Examples in NLP
• Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment
• OCC: A Smart Reply System for Efficient In-App Communications
• Revisiting Skip-Gram Negative Sampling Model with Rectification
• OCoR: An Overlapping-Aware Code Retriever
• Triple Generative Adversarial Networks
• InferCode: Self-Supervised Learning of Code Representations by Predicting Subtrees
• Predicting US State-Level Agricultural Sentiment as a Measure of Food Security with Tweets from Farming Communities
• Dynamic Compositional Neural Networks over Tree Structure
• Literature review on vulnerability detection using NLP technology
• Explicit Utilization of General Knowledge in Machine Reading Comprehension
• Weak Supervision for Fake News Detection via Reinforcement Learning
• Text as Environment: A Deep Reinforcement Learning Text Readability Assessment Model
• Deriving Machine Attention from Human Rationales
• Image Transformation can make Neural Networks more robust against Adversarial Examples
• Leveraging Multi-Source Weak Social Supervision for Early Detection of Fake News
• Alzheimer's Disease Detection from Spontaneous Speech through Combining Linguistic Complexity and (Dis)Fluency Features with Pretrained Language Models
• Out-of-domain Detection for Natural Language Understanding in Dialog Systems
• Label-guided Learning for Text Classification
• Implicit Regularization of Stochastic Gradient Descent in Natural Language Processing: Observations and Implications
• CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation
• Alquist 3.0: Alexa Prize Bot Using Conversational Knowledge Graph
• Concise and Effective Network for 3D Human Modeling from Orthogonal Silhouettes
• Resilient and Adaptive Framework for Large Scale Android Malware Fingerprinting using Deep Learning and NLP Techniques
• Leveraging Intra-User and Inter-User Representation Learning for Automated Hate Speech Detection
• Same Representation, Different Attentions: Shareable Sentence Representation Learning from Multiple Tasks
• LadRa-Net: Locally-Aware Dynamic Re-read Attention Net for Sentence Semantic Matching
• ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction
• Generation-Distillation for Efficient Natural Language Understanding in Low-Data Settings
• Deep Learning for Digital Text Analytics: Sentiment Analysis
• SQL-to-Text Generation with Graph-to-Sequence Model
• Chinese Discourse Segmentation Using Bilingual Discourse Commonality
• Visual and Textual Sentiment Analysis Using Deep Fusion Convolutional Neural Networks
• Deep Extreme Multi-label Learning
• A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
• Learning Phrase Embeddings from Paraphrases with GRUs
• Cross-lingual Distillation for Text Classification
• Computation Error Analysis of Block Floating Point Arithmetic Oriented Convolution Neural Network Accelerator Design
• Controlled CNN-based Sequence Labeling for Aspect Extraction
• Online Deception Detection Refueled by Real World Data Collection
• Phonetic-enriched Text Representation for Chinese Sentiment Analysis with Reinforcement Learning
• Data Sanity Check for Deep Learning Systems via Learnt Assertions
• Representing Sentences as Low-Rank Subspaces
• Contextual Text Style Transfer
• Learning Semantically Coherent and Reusable Kernels in Convolution Neural Nets for Sentence Classification
• Estimation of Inter-Sentiment Correlations Employing Deep Neural Network Models
• #phramacovigilance - Exploring Deep Learning Techniques for Identifying Mentions of Medication Intake from Twitter
• Light-Weighted CNN for Text Classification
• Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review Generation
• CatGAN: Category-aware Generative Adversarial Networks with Hierarchical Evolutionary Learning for Category Text Generation
• Unpaired Cross-lingual Image Caption Generation with Self-Supervised Rewards
• Deep neural network for solving differential equations motivated by Legendre-Galerkin approximation
• What Do You Mean I'm Funny? Personalizing the Joke Skill of a Voice-Controlled Virtual Assistant
• Exploiting Synchronized Lyrics And Vocal Features For Music Emotion Detection
• When and Why does a Model Fail? A Human-in-the-loop Error Detection Framework for Sentiment Analysis
• SeVeN: Augmenting Word Embeddings with Unsupervised Relation Vectors
• Exploring Polarization of Users Behavior on Twitter During the 2019 South American Protests
• CMU LiveMedQA at TREC 2017 LiveQA: A Consumer Health Question Answering System
• Real-Time Steganalysis for Stream Media Based on Multi-channel Convolutional Sliding Windows
• Learning Effective Representations for Person-Job Fit by Feature Fusion
• Did You Really Just Have a Heart Attack? Towards Robust Detection of Personal Health Mentions in Social Media
• Adversarial Active Learning based Heterogeneous Graph Neural Network for Fake News Detection
• CANDiS: Coupled & Attention-Driven Neural Distant Supervision
• Neural Multi-Step Reasoning for Question Answering on Semi-Structured Tables
• An Automatic Text Classification Method Based on Hierarchical Taxonomies, Neural Networks and Document Embedding: The NETHIC Tool
• SERCNN: Stacked Embedding Recurrent Convolutional Neural Network in Detecting Depression on Twitter
• Contextual and Position-Aware Factorization Machines for Sentiment Classification
• ST${}^2$: Small-data Text Style Transfer via Multi-task Meta-Learning
• The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification
• Sentiment and Emotion Classification of Epidemic Related Bilingual data from Social Media
• Predicting Helpfulness of Online Reviews
• Grey-box Adversarial Attack And Defence For Sentiment Classification
• MALCOM: Generating Malicious Comments to Attack Neural Fake News Detection Models
• Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing
• Fine-Grained Sentence Functions for Short-Text Conversation
• Fault Localization with Code Coverage Representation Learning
• Advancing PICO Element Detection in Biomedical Text via Deep Neural Networks
• Hierarchical Text Classification of Urdu News using Deep Neural Network
• Cell Type Identification from Single-Cell Transcriptomic Data via Semi-supervised Learning
• Development of deep learning algorithms to categorize free-text notes pertaining to diabetes: convolution neural networks achieve higher accuracy than support vector machines
• A Deep Neural Information Fusion Architecture for Textual Network Embeddings
• Predicting Missing Information of Key Aspects in Vulnerability Reports
• Empirical Study of Text Augmentation on Social Media Text in Vietnamese
• Combination of multiple Deep Learning architectures for Offensive Language Detection in Tweets
• COSEA: Convolutional Code Search with Layer-wise Attention
• On Early-stage Debunking Rumors on Twitter: Leveraging the Wisdom of Weak Learners
• Predicting user intent from search queries using both CNNs and RNNs
• Combine Convolution with Recurrent Networks for Text Classification
• Super Characters: A Conversion from Sentiment Classification to Image Classification
• A Comprehensive Low and High-level Feature Analysis for Early Rumor Detection on Twitter
• MoodSwipe: A Soft Keyboard that Suggests Messages Based on User-Specified Emotions
• An Investigation of Transfer Learning-Based Sentiment Analysis in Japanese
• Water Preservation in Soan River Basin using Deep Learning Techniques
• Learning Invariant Representations of Social Media Users
• Twitter Sentiment Analysis using Distributed Word and Sentence Representation
• Transfer Learning for Multi-lingual Tasks -- a Survey
• Activation functions are not needed: the ratio net
• Longitudinal Analysis of Discussion Topics in an Online Breast Cancer Community using Convolutional Neural Networks
• SMILE: Self-Distilled MIxup for Efficient Transfer LEarning
• Discovery of Latent Factors in High-dimensional Data Using Tensor Methods
• dpMood: Exploiting Local and Periodic Typing Dynamics for Personalized Mood Prediction
• Product Function Need Recognition via Semi-supervised Attention Network
• Sparse Lifting of Dense Vectors: Unifying Word and Sentence Representations
• Predicting Discharge Medications at Admission Time Based on Deep Learning
• Topic Identification for Speech without ASR
• Modeling Human Mental States with an Entity-based Narrative Graph
• ETH-DS3Lab at SemEval-2018 Task 7: Effectively Combining Recurrent and Convolutional Neural Networks for Relation Classification and Extraction
• Sentiment Classification with Word Attention based on Weakly Supervised Learning with a Convolutional Neural Network
• Machine Learning Meets Natural Language Processing -- The story so far
• Multi-type Disentanglement without Adversarial Training
• Multi-view Models for Political Ideology Detection of News Articles
• Inflo: News Categorization and Keyphrase Extraction for Implementation in an Aggregation System
• Neural Text Classification by Jointly Learning to Cluster and Align
• Toward Tag-free Aspect Based Sentiment Analysis: A Multiple Attention Network Approach
• Fake or Real? A Study of Arabic Satirical Fake News
• Meta-Embeddings Based On Self-Attention
• SEOVER: Sentence-level Emotion Orientation Vector based Conversation Emotion Recognition Model
• DeepChrome: Deep-learning for predicting gene expression from histone modifications
• Fast Extraction of Word Embedding from Q-contexts
• Transformer for Emotion Recognition
• Exploring Text Specific and Blackbox Fairness Algorithms in Multimodal Clinical NLP
• Impact of Feature Selection on Micro-Text Classification
• Fake News Detection through Graph Comment Advanced Learning
• AMSI-Based Detection of Malicious PowerShell Code Using Contextual Embeddings
• Semi-supervised Text Style Transfer: Cross Projection in Latent Space
• Learning Representations and Agents for Information Retrieval
• Entropy-Based Modeling for Estimating Soft Errors Impact on Binarized Neural Network Inference
• Exploring Neural Net Augmentation to BERT for Question Answering on SQUAD 2.0
• Hybrid Code Networks using a convolutional neural network as an input layer achieves higher turn accuracy
• Geometry matters: Exploring language examples at the decision boundary
• Embedding Compression with Isotropic Iterative Quantization
• ReINTEL Challenge 2020: A Multimodal Ensemble Model for Detecting Unreliable Information on Vietnamese SNS
• TechTexC: Classification of Technical Texts using Convolution and Bidirectional Long Short Term Memory Network
• Hybrid Tiled Convolutional Neural Networks for Text Sentiment Classification
• Text Classification based on Multi-granularity Attention Hybrid Neural Network
• Image-based Natural Language Understanding Using 2D Convolutional Neural Networks
• Classifying Textual Data with Pre-trained Vision Models through Transfer Learning and Data Transformations
• A Multichannel Convolutional Neural Network For Cross-language Dialog State Tracking
• Fairness-aware Summarization for Justified Decision-Making
• Pay More Attention - Neural Architectures for Question-Answering
• Unsupervised Neural Text Simplification
• Augmenting the User-Item Graph with Textual Similarity Models
• Monolingual sentence matching for text simplification
• Dual Memory Network Model for Biased Product Review Classification
• Prioritize Crowdsourced Test Reports via Deep Screenshot Understanding
• Solving Sinhala Language Arithmetic Problems using Neural Networks
• The effects of data size on Automated Essay Scoring engines
• Sentylic at IEST 2018: Gated Recurrent Neural Network and Capsule Network Based Approach for Implicit Emotion Detection
• Machine Learning for Protein Function
• PERS: A Personalized and Explainable POI Recommender System
• Hierarchical Neural Networks for Sequential Sentence Classification in Medical Scientific Abstracts
• Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection
• Medical Multimodal Classifiers Under Scarce Data Condition
• BERT Fine-Tuning for Sentiment Analysis on Indonesian Mobile Apps Reviews
• A Convolutional Neural Network for Aspect Sentiment Classification
• Graph Neural Networks to Predict Customer Satisfaction Following Interactions with a Corporate Call Center
• Psychological State in Text: A Limitation of Sentiment Analysis
• Graph Convolution for Multimodal Information Extraction from Visually Rich Documents
• Adversarial Training of Word2Vec for Basket Completion
• Ranking-Based Autoencoder for Extreme Multi-label Classification
• Dense Adaptive Cascade Forest: A Self Adaptive Deep Ensemble for Classification Problems
• DeepEmo: Learning and Enriching Pattern-Based Emotion Representations
• Transformer-F: A Transformer network with effective methods for learning universal sentence representation
• Network Clustering for Multi-task Learning
• SLAM-Inspired Simultaneous Contextualization and Interpreting for Incremental Conversation Sentences
• Using Context Events in Neural Network Models for Event Temporal Status Identification
• Locating Faulty Methods with a Mixed RNN and Attention Model
• Enhancing Model Robustness By Incorporating Adversarial Knowledge Into Semantic Representation
• Open-domain Topic Identification of Out-of-domain Utterances using Wikipedia
• "Killing Me" Is Not a Spoiler: Spoiler Detection Model using Graph Neural Networks with Dependency Relation-Aware Attention Mechanism
• geoGAT: Graph Model Based on Attention Mechanism for Geographic Text Classification
• Can a Fruit Fly Learn Word Embeddings?
• EmotionGIF-IITP-AINLPML: Ensemble-based Automated Deep Neural System for predicting category(ies) of a GIF response
• R${}^2$-Net: Relation of Relation Learning Network for Sentence Semantic Matching
• Multi-Aspect Sentiment Analysis with Latent Sentiment-Aspect Attribution
• Blind signal decomposition of various word embeddings based on join and individual variance explained
• UPB at SemEval-2020 Task 12: Multilingual Offensive Language Detection on Social Media by Fine-tuning a Variety of BERT-based Models
• Using Clinical Drug Representations for Improving Mortality and Length of Stay Predictions
• Brief View and Analysis to Latest Android Security Issues and Approaches
• Ranking labs-of-origin for genetically engineered DNA using Metric Learning
• DISCO : efficient unsupervised decoding for discrete natural language problems via convex relaxation
• Timestamping Documents and Beliefs
• DrugDBEmbed : Semantic Queries on Relational Database using Supervised Column Encodings
• DyDiff-VAE: A Dynamic Variational Framework for Information Diffusion Prediction
• Network representation learning: A macro and micro view
• Linguistic Knowledge in Data Augmentation for Natural Language Processing: An Example on Chinese Question Matching
• Deep Learning based, end-to-end metaphor detection in Greek language with Recurrent and Convolutional Neural Networks
• When to Fold'em: How to answer Unanswerable questions
• Regular Expressions for Fast-response COVID-19 Text Classification
• Learning Neural Networks on SVD Boosted Latent Spaces for Semantic Classification
• Unsupervised and Supervised Structure Learning for Protein Contact Prediction
• Aggressive Language Detection with Joint Text Normalization via Adversarial Multi-task Learning
• End to End Binarized Neural Networks for Text Classification
• A Deep Learning-Based Approach for Measuring the Domain Similarity of Persian Texts
• A Corpus for Detecting High-Context Medical Conditions in Intensive Care Patient Notes Focusing on Frequently Readmitted Patients
• A machine learning method correlating pulse pressure wave data with pregnancy
• Subword Language Model for Query Auto-Completion
• Stylized Text Generation Using Wasserstein Autoencoders with a Mixture of Gaussian Prior
• Self-Balanced Dropout
• How to Evaluate Word Representations of Informal Domain?
• Large-scale Gender/Age Prediction of Tumblr Users
• EventMapper: Detecting Real-World Physical Events Using Corroborative and Probabilistic Sources
• Improved and Robust Controversy Detection in General Web Pages Using Semantic Approaches under Large Scale Conditions
• Towards Controlled Transformation of Sentiment in Sentences
• Patient Risk Assessment and Warning Symptom Detection Using Deep Attention-Based Neural Networks
• Deep CNN Frame Interpolation with Lessons Learned from Natural Language Processing
• Training and Prediction Data Discrepancies: Challenges of Text Classification with Noisy, Historical Data
• Do users talk about the software in my product? Analyzing user reviews on IoT products
• Towards end-to-end pulsed eddy current classification and regression with CNN
• Text Classification based on Multiple Block Convolutional Highways
• Low-Resource Contextual Topic Identification on Speech
• SmartBullets: A Cloud-Assisted Bullet Screen Filter based on Deep Learning
• Deep Unified Multimodal Embeddings for Understanding both Content and Users in Social Media Networks
• Conversational Help for Task Completion and Feature Discovery in Personal Assistants
• On the difficulty of a distributional semantics of spoken language
• CRNN: A Joint Neural Network for Redundancy Detection
• Search Intelligence: Deep Learning For Dominant Category Prediction
• End-to-end Learning for Short Text Expansion
• Batch-Augmented Multi-Agent Reinforcement Learning for Efficient Traffic Signal Optimization
• OhioState at IJCNLP-2017 Task 4: Exploring Neural Architectures for Multilingual Customer Feedback Analysis
• Exploiting Domain Knowledge via Grouped Weight Sharing with Application to Text Categorization
• HLA class I binding prediction via convolutional neural networks