921 citations · 9.3k across the 292 of their papers we have counts for
41 papers · 1 filter
Unsupervised Pseudo-Labeling for Extractive Summarization on Electronic Health Records
Xiangan Liu, Keyang Xu, Pengtao Xie +1
Extractive summarization is very useful for physicians to better manage and digest Electronic Health Records (EHRs). However, the training of a supervised model requires disease-sp…
Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-Generator Architectures
Hongyang Zhang, Susu Xu, Jiantao Jiao +3
We study the problem of alleviating the instability issue in the GAN training procedure via new architecture design. The discrepancy between the minimax and maximin objective value…
On the Complexity of Exploration in Goal-Driven Navigation
Maruan Al-Shedivat, Lisa Lee, Ruslan Salakhutdinov +1
Building agents that can explore their environments intelligently is a challenging open problem. In this paper, we make a step towards understanding how a hierarchical design of th…
Discourse in Multimedia: A Case Study in Information Extraction
Mrinmaya Sachan, Kumar Avinava Dubey, Eduard H. Hovy +3
To ensure readability, text is often written and presented with due formatting. These text formatting devices help the writer to effectively convey the narrative. At the same time,…
Connecting the Dots Between MLE and RL for Sequence Prediction
Bowen Tan, Zhiting Hu, Zichao Yang +2
Sequence prediction models can be learned from example sequences with a variety of training algorithms. Maximum likelihood learning is simple and efficient, yet can suffer from com…
Fault Tolerance in Iterative-Convergent Machine Learning
Aurick Qiao, Bryon Aragam, Bingjing Zhang +1
Machine learning (ML) training algorithms often possess an inherent self-correcting behavior due to their iterative-convergent nature. Recent systems exploit this property to achie…