189 citations · 1.7k across the 110 of their papers we have counts for
15 papers · 1 filter
EQG-RACE: Examination-Type Question Generation
Xin Jia, Wenjie Zhou, Xu Sun +1
Question Generation (QG) is an essential component of the automatic intelligent tutoring systems, which aims to generate high-quality questions for facilitating the reading practic…
CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade
Lei Li, Yankai Lin, Deli Chen +4
Dynamic early exiting aims to accelerate the inference of pre-trained language models (PLMs) by emitting predictions in internal layers without passing through the entire model. In…
Learning Robust Representation for Clustering through Locality Preserving Variational Discriminative Network
Ruixuan Luo, Wei Li, Zhiyuan Zhang +3
Clustering is one of the fundamental problems in unsupervised learning. Recent deep learning based methods focus on learning clustering oriented representations. Among those method…
Rethinking the Promotion Brought by Contrastive Learning to Semi-Supervised Node Classification
Deli Chen, Yankai Lin, Lei Li +4
Graph Contrastive Learning (GCL) has proven highly effective in promoting the performance of Semi-Supervised Node Classification (SSNC). However, existing GCL methods are generally…
A Backbone Replaceable Fine-tuning Framework for Stable Face Alignment
Xu Sun, Zhenfeng Fan, Zihao Zhang +2
Heatmap regression based face alignment has achieved prominent performance on static images. However, the stability and accuracy are remarkably discounted when applying the existin…
CAPT: Contrastive Pre-Training for Learning Denoised Sequence Representations
Fuli Luo, Pengcheng Yang, Shicheng Li +2
Pre-trained self-supervised models such as BERT have achieved striking success in learning sequence representations, especially for natural language processing. These models typica…
Regularizing Dialogue Generation by Imitating Implicit Scenarios
Shaoxiong Feng, Xuancheng Ren, Hongshen Chen +3
Human dialogues are scenario-based and appropriate responses generally relate to the latent context knowledge entailed by the specific scenario. To enable responses that are more m…
Graph-based Multi-hop Reasoning for Long Text Generation
Liang Zhao, Jingjing Xu, Junyang Lin +3
Long text generation is an important but challenging task.The main problem lies in learning sentence-level semantic dependencies which traditional generative models often suffer fr…
Collaborative Group Learning
Shaoxiong Feng, Hongshen Chen, Xuancheng Ren +3
Collaborative learning has successfully applied knowledge transfer to guide a pool of small student networks towards robust local minima. However, previous approaches typically str…
Building BROOK: A Multi-modal and Facial Video Database for Human-Vehicle Interaction Research
Xiangjun Peng, Zhentao Huang, Xu Sun
With the growing popularity of Autonomous Vehicles, more opportunities have bloomed in the context of Human-Vehicle Interactions. However, the lack of comprehensive and concrete da…
Parallel Data Augmentation for Formality Style Transfer
Yi Zhang, Tao Ge, Xu Sun
The main barrier to progress in the task of Formality Style Transfer is the inadequacy of training data. In this paper, we study how to augment parallel data and propose novel and…
Rethinking and Improving Natural Language Generation with Layer-Wise Multi-View Decoding
Fenglin Liu, Xuancheng Ren, Guangxiang Zhao +4
In sequence-to-sequence learning, e.g., natural language generation, the decoder relies on the attention mechanism to efficiently extract information from the encoder. While it is…
Jointly Modeling Aspect and Sentiment with Dynamic Heterogeneous Graph Neural Networks
Shu Liu, Wei Li, Yunfang Wu +2
Target-Based Sentiment Analysis aims to detect the opinion aspects (aspect extraction) and the sentiment polarities (sentiment detection) towards them. Both the previous pipeline a…
Query-Variant Advertisement Text Generation with Association Knowledge
Siyu Duan, Wei Li, Cai Jing +3
Online advertising is an important revenue source for many IT companies. In the search advertising scenario, advertisement text that meets the need of the search query would be mor…
Exploring and Distilling Cross-Modal Information for Image Captioning
Fenglin Liu, Xuancheng Ren, Yuanxin Liu +2
Recently, attention-based encoder-decoder models have been used extensively in image captioning. Yet there is still great difficulty for the current methods to achieve deep image u…