1. Neural Machine Translationby Jointly Learning to Align and Translate
2. Context-aware Natural Language Generation with Recurrent Neural Networks
3. Ensemble Distillation for Neural Machine Translation
4. Sequence-level knowledge distillation
5. Context-Dependent Sense Embedding∗
6. Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora
7. Discourse Parsing with Attention-based Hierarchical Neural Networks
8. Keyphrase Extraction Using Deep Recurrent Neural Networks on Twitter
9. Generating Text with Recurrent Neural Networks
10. Towards End-to-End Speech Recognition with Recurrent Neural Networks
11. Long Short-Term Memory Neural Networks for Chinese Word Segmentation
12. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
13. Modeling Coverage for Neural Machine Translation
14. Multi-Granularity Chinese Word Embedding
15. A Hierarchical Model of Reviews for Aspect-based Sentiment Analysis
16. Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
17. Learning Crosslingual Word Embeddings without Bilingual Corpora
18. Generalizing and Hybridizing Count-based and Neural Language Models
19. Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification
20. A Systematic Study of Neural Discourse Models for Implicit Discourse Relation
21. Tree-to-Sequence Attentional Neural Machine Translation
22. Long-Short Range Context Neural Networks for Language Modeling
23. CHARAGRAM: Embedding Words and Sentences via Character n-grams
24. Improving Sparse Word Representations with Distributional Inference for Semantic Composition
25. Modelling Interaction of Sentence Pair with Coupled-LSTMs
26. Improving LSTM-based Video Description with Linguistic Knowledge Mined from Text
27. Learning Robust Representations of Text
28. Bi-directional Attention with Agreement for Dependency Parsing
29. Anchoring and Agreement in Syntactic Annotations
30. Learning principled bilingual mappings of word embeddings while preserving monolingual invariance
31. Parsing as Language Modeling
32. Encoding Temporal Information for Time-Aware Link Prediction
33. Language Transfer Learning for Supervised Lexical Substitution
34. Adaptive Joint Learning of Compositional and Non-Compositional Phrase Embeddings