883 citations · 1.1k across the 30 of their papers we have counts for
30 papers
Draft, Command, and Edit: Controllable Text Editing in E-Commerce
Kexin Yang, Dayiheng Liu, Wenqiang Lei +3
Product description generation is a challenging and under-explored task. Most such work takes a set of product attributes as inputs then generates a description from scratch in a s…
Face Deblurring Based on Separable Normalization and Adaptive Denormalization
Xian Zhang, Hao Zhang, Jiancheng Lv +1
Face deblurring aims to restore a clear face image from a blurred input image with more explicit structure and facial details. However, most conventional image and face deblurring…
Heart-Darts: Classification of Heartbeats Using Differentiable Architecture Search
Jindi Lv, Qing Ye, Yanan Sun +2
Arrhythmia is a cardiovascular disease that manifests irregular heartbeats. In arrhythmia detection, the electrocardiogram (ECG) signal is an important diagnostic technique. Howeve…
Poolingformer: Long Document Modeling with Pooling Attention
Hang Zhang, Yeyun Gong, Yelong Shen +4
In this paper, we introduce a two-level attention schema, Poolingformer, for long document modeling. Its first level uses a smaller sliding window pattern to aggregate information…
LANA: Towards Personalized Deep Knowledge Tracing Through Distinguishable Interactive Sequences
Yuhao Zhou, Xihua Li, Yunbo Cao +3
In educational applications, Knowledge Tracing (KT), the problem of accurately predicting students' responses to future questions by summarizing their knowledge states, has been wi…
Dynamic Normalization
Chuan Liu, Yi Gao, Jiancheng Lv
Batch Normalization has become one of the essential components in CNN. It allows the network to use a higher learning rate and speed up training. And the network doesn't need to be…
GLGE: A New General Language Generation Evaluation Benchmark
Dayiheng Liu, Yu Yan, Yeyun Gong +15
Multi-task benchmarks such as GLUE and SuperGLUE have driven great progress of pretraining and transfer learning in Natural Language Processing (NLP). These benchmarks mostly focus…
Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space
Dayiheng Liu, Yeyun Gong, Jie Fu +5
In this paper, we propose a novel data augmentation method, referred to as Controllable Rewriting based Question Data Augmentation (CRQDA), for machine reading comprehension (MRC),…
PSO-PS: Parameter Synchronization with Particle Swarm Optimization for Distributed Training of Deep Neural Networks
Qing Ye, Yuxuan Han, Yanan sun +1
Parameter updating is an important stage in parallelism-based distributed deep learning. Synchronous methods are widely used in distributed training the Deep Neural Networks (DNNs)…
AnchiBERT: A Pre-Trained Model for Ancient ChineseLanguage Understanding and Generation
Huishuang Tian, Kexin Yang, Dayiheng Liu +1
Ancient Chinese is the essence of Chinese culture. There are several natural language processing tasks of ancient Chinese domain, such as ancient-modern Chinese translation, poem g…
HPSGD: Hierarchical Parallel SGD With Stale Gradients Featuring
Yuhao Zhou, Qing Ye, Hailun Zhang +1
While distributed training significantly speeds up the training process of the deep neural network (DNN), the utilization of the cluster is relatively low due to the time-consuming…
DBS: Dynamic Batch Size For Distributed Deep Neural Network Training
Qing Ye, Yuhao Zhou, Mingjia Shi +2
Synchronous strategies with data parallelism, such as the Synchronous StochasticGradient Descent (S-SGD) and the model averaging methods, are widely utilizedin distributed training…
RikiNet: Reading Wikipedia Pages for Natural Question Answering
Dayiheng Liu, Yeyun Gong, Jie Fu +5
Reading long documents to answer open-domain questions remains challenging in natural language understanding. In this paper, we introduce a new model, called RikiNet, which reads W…
Learning Event-Based Motion Deblurring
Zhe Jiang, Yu Zhang, Dongqing Zou +3
Recovering sharp video sequence from a motion-blurred image is highly ill-posed due to the significant loss of motion information in the blurring process. For event-based cameras,…
Let's be Humorous: Knowledge Enhanced Humor Generation
Hang Zhang, Dayiheng Liu, Jiancheng Lv +1
The generation of humor is an under-explored and challenging problem. Previous works mainly utilize templates or replace phrases to generate humor. However, few works focus on free…
Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation
Dayiheng Liu, Yeyun Gong, Jie Fu +6
News headline generation aims to produce a short sentence to attract readers to read the news. One news article often contains multiple keyphrases that are of interest to different…
Generating Chinese Poetry from Images via Concrete and Abstract Information
Yusen Liu, Dayiheng Liu, Jiancheng Lv +1
In recent years, the automatic generation of classical Chinese poetry has made great progress. Besides focusing on improving the quality of the generated poetry, there is a new top…
Domain Embedded Multi-model Generative Adversarial Networks for Image-based Face Inpainting
Xian Zhang, Xin Wang, Bin Kong +6
Prior knowledge of face shape and structure plays an important role in face inpainting. However, traditional face inpainting methods mainly focus on the generated image resolution…
Deep Poetry: A Chinese Classical Poetry Generation System
Yusen Liu, Dayiheng Liu, Jiancheng Lv
In this work, we demonstrate a Chinese classical poetry generation system called Deep Poetry. Existing systems for Chinese classical poetry generation are mostly template-based and…
Deep Density-aware Count Regressor
Zhuojun Chen, Junhao Cheng, Yuchen Yuan +3
We seek to improve crowd counting as we perceive limits of currently prevalent density map estimation approach on both prediction accuracy and time efficiency. We leverage multilev…
Deep Learning-Based Automatic Downbeat Tracking: A Brief Review
Bijue Jia, Jiancheng Lv, Dayiheng Liu
As an important format of multimedia, music has filled almost everyone's life. Automatic analyzing music is a significant step to satisfy people's need for music retrieval and musi…
TIGS: An Inference Algorithm for Text Infilling with Gradient Search
Dayiheng Liu, Jie Fu, Pengfei Liu +1
Text infilling is defined as a task for filling in the missing part of a sentence or paragraph, which is suitable for many real-world natural language generation scenarios. However…
mu-Forcing: Training Variational Recurrent Autoencoders for Text Generation
Dayiheng Liu, Xu Yang, Feng He +2
It has been previously observed that training Variational Recurrent Autoencoders (VRAE) for text generation suffers from serious uninformative latent variables problem. The model w…
Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning
Dayiheng Liu, Jie Fu, Yidan Zhang +2
Typical methods for unsupervised text style transfer often rely on two key ingredients: 1) seeking the explicit disentanglement of the content and the attributes, and 2) troublesom…