Xu Sun | Xuancheng Ren

Latest

A Global Past-Future Early Exit Method for Accelerating Inference of Pre-trained Language Models
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side Effects
Collaborative Group Learning
Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption
Multi-View Feature Representation for Dialogue Generation with Bidirectional Distillation
Towards Semantics-Enhanced Pre-Training: Can Lexicon Definitions Help Learning Sentence Meanings?
Prophet Attention: Predicting Attention with Future Attention for Improved Image Captioning
Regularizing Dialogue Generation by Imitating Implicit Scenarios
Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations
Exploring and Distilling Cross-Modal Information for Image Captioning
A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer
PKUSeg
PKUSEG: A Toolkit for Multi-Domain Chinese Word Segmentation
Towards Easier and Faster Sequence Labeling for Natural Language Processing: A Search-Based Probabilistic Online Learning Framework (SAPO)
Training Simplification and Model Simplification for Deep Learning: A Minimal Effort Back Propagation Method
Cross-Domain and Semisupervised Named Entity Recognition in Chinese Social Media: A Unified Model
JDDC 2018
A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation
Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation
simNet: Stepwise Image-Topic Merging Network for Generating Detailed and Comprehensive Image Captions
Deconvolution-Based Global Decoding for Neural Machine Translation
Does Higher Order LSTM Have Better Accuracy for Segmenting and Labeling Sequence Data?
Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach
A Hierarchical End-to-End Model for Jointly Improving Text Summarization and Sentiment Classification
Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation
Building an Ellipsis-Aware Chinese Dependency Treebank for Web Text
meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting