最近關注了一下NAACL2019，看了accepted papers，選了一些感興趣的論文，有事沒事看看，記錄一下。
A Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification
Abusive Language Detection with Graph Convolutional Networks
Adaptive Convolution for Text Classification
Adversarial Category Alignment Network for Cross-domain Sentiment Classification
An Effective Label Noise Model for DNN Text Classification
An Embarrassingly Simple Approach for Transfer Learning from Pretrained Language Models
Attention is not Explanation
Convolutional Self-Attention Networks
Dialogue Act Classification with Context-Aware Self-Attention
Enhancing Opinion Role Labeling with Semantic-Aware Word Representations from Semantic Role Labeling
Evaluating Text GANs as Language Models
How Large A Vocabulary Does Text Classification Need? A Variational Approach on Vocabulary Selection ：
文本分類任務中詞表大小的選擇，文章通過類似dropout的思想對每個詞學習一個drop參數，通過閾值留下drop值小的詞，選擇最優的詞表。
Incorporating Emoji Descriptions Improves Tweet Classification
Integrating Semantic Knowledge to Tackle Zero-shot Text Classification
Inter-Sentence Attention For Semantic Role Labeling
Mitigating Uncertainty in Document Classification
Partial Or Complete, That’s The Question
Probabilistic Natural Language Generation with Wasserstein Autoencoders
Ranking-Based AutoEncoder for Extreme Multi-label Classification
Rethinking Complex Neural Network Architectures for Document Classification
Syntax-aware Neural Semantic Role Labeling with Supertags
Text Classification with Few Examples using Controlled Generalization
A Radical‐aware Attention‐based Model for Chinese Text Classification
What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models
Character‐Level Language Modeling with Deeper Self‐Attention
Resisting Adversarial Attacks using Gaussian Mixture Variational Autoencoders
Revisiting LSTM Networks for SemiS-upervised Text Classification via Mixed Objective Function
InfoVAE: Balancing Learning and Inference in Variational Autoencoders
Direct Training for Spiking Neural Networks: Faster, Larger, Better