1

Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses
Sentence position is a strong feature for news summarization, since the lead often (but not always) summarizes the key points of the …
Matt Grenander, Yue Dong, Jackie Chi Kit Cheung, Annie Louis
Cite Arxiv ACL Anthology
EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
We present the first sentence simplification model that learns explicit edit operations (ADD, DELETE, and KEEP) via a neural …
Yue Dong, Zichao Li, Mehdi Rezagholizadeh, Jackie Chi Kit Cheung
Cite Arxiv ACL Anthology Code Video
Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses
We present two architectures for multi-task learning with neural sequence models. Our approach allows the relationships between …
Pengfei Liu, Fu Jie, Yue Dong, Xipeng Qiu, Jackie Chi Kit Cheung
Cite paper
A Hierarchical Neural Attention-based Text Classifier
Deep neural networks have been displaying superior performance over traditional supervised classifiers in text classification. They …
Koustuv Sinha, Yue Dong, Jackie Chi Kit Cheung, Derek Ruths
Cite ACL Anthology Code
BanditSum: Extractive Summarization as a Contextual Bandit
In this work, we propose a novel method for training neural networks to perform single-document extractive summarization without …
Yue Dong, Yikang Shen, Eric Crawford, Herke van Hoof, Jackie Chi Kit Cheung
Cite Arxiv ACL Anthology Code Video
Threaded ensembles of supervised and unsupervised neural networks for stream learning
Most existing model-based approaches to anomaly detection in streaming data are based on decision trees due to their fast construction …
Yue Dong, Nathalie Japkowicz
Cite Paper Best Paper Award