Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks [ICLR 2019]
Multi-Granularity Self-Attention for Neural Machine Translation [EMNLP 2019]
Tree Transformer Integrating Tree Structures into Self-Attention [EMNLP 2019]
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned [ACL 2019]
Self-Attention with Structural Position Representations [EMNLP 2019]
Are Sixteen Heads Really Better than One? [NIPS 2019]
Towards Better Modeling Hierarchical Structure for Self-Attention [EMNLP 2019]
An Analysis of Encoder Representations in Transformer-Based Machine Translation [EMNLP 2018]
How Much Attention Do You Need? A Granular Analysis of Neural Machine Translation Architectures？[ACL 2018]
Self-Attention with Relative Position Representations [NAACL 2018]
Single Training Dimension Selection for Word Embedding with PCA [EMNLP 2019]
Improving Word Embedding by Adversarial Training [NIPS 2018]
Knowledge Graph Embedding Based Question Answering [WSDM 2019]
A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysis [EMNLP 2019]
Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks [EMNLP 2019]
CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis [EMNLP 2019]
Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks [EMNLP 2019]
Attentional Encoder Network for Targeted Sentiment Classification
Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis
Transfer Capsule Network for Aspect Level Sentiment Classification [ACL 2019]
Progressive Self-Supervised Attention Learning forAspect-Level Sentiment Analysis [ACL 2019]
Multi-grained Attention Network for Aspect-LevelSentiment Classification [EMNLP 2018]
IARM: Inter-Aspect Relation Modeling with Memory Networks in Aspect-Based Sentiment Analysis [EMNLP 2018]
A Position-aware Bidirectional Attention Network for Aspect-levelSentiment Analysis [COLING 2018]
Neural Machine Translation [Tutorials by Philipp Koehn]
Neural Machine Translation by Jointly Learning to Align and Translate [ICLR 2015]
FREELB: ENHANCED ADVERSARIAL TRAINING FOR LANGUAGE UNDERSTANDING [ICLR 2020 under review]
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment [AAAI 2020]
MIXUP INFERENCE: BETTER EXPLOITING MIXUP TO DEFEND ADVERSARIAL ATTACKS [ICLR 2020 under review] TODO
On the Robustness of Self-Attentive Models [ACL 2019]
TEXTBUGGER: Generating Adversarial Text Against Real-world Applications [NDSS 2019]
Generating Natural Language Adversarial Examples [EMNLP 2018]
Adversarial examples in the physical world [ICLR 2017]
CROSS-LINGUAL ALIGNMENT VS JOINT TRAINING: A COMPARATIVE STUDY AND A SIMPLE UNIFIED FRAMEWORK
Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spaces [ACL 2019]