papers

Publications (6)

cond-mat.mtrl-sci2017

Neutron Scattering Halo Observed in Highly Oriented Pyrolytic Graphite

Lilin He, William Hamilton, Tao Hong +4

Highly oriented pyrolytic graphite (HOPG) has been widely used as monochromators, analyzers and filters at neutron and X-ray scattering facilities. In this Letter we report the fir…

cs.CL2021

End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering

Devendra Singh Sachan, Siva Reddy, William Hamilton +2

We present an end-to-end differentiable training method for retrieval-augmented open-domain question answering systems that combine information from multiple retrieved documents wh…

cs.LG2020

A Universal Representation Transformer Layer for Few-Shot Image Classification

Lu Liu, William Hamilton, Guodong Long +2

Few-shot classification aims to recognize unseen classes when presented with only a small number of samples. We consider the problem of multi-domain few-shot image classification,…

cs.CL2020

Stronger Transformers for Neural Multi-Hop Question Generation

Devendra Singh Sachan, Lingfei Wu, Mrinmaya Sachan +1

Prior work on automated question generation has almost exclusively focused on generating simple questions whose answers can be extracted from a single document. However, there is a…

cs.CL2021

Do Syntax Trees Help Pre-trained Transformers Extract Information?

Devendra Singh Sachan, Yuhao Zhang, Peng Qi +1

Much recent work suggests that incorporating syntax information from dependency trees can improve task-specific transformer models. However, the effect of incorporating dependency…

cs.LG2019

Actor Critic with Differentially Private Critic

Jonathan Lebensold, William Hamilton, Borja Balle +1

Reinforcement learning algorithms are known to be sample inefficient, and often performance on one task can be substantially improved by leveraging information (e.g., via pre-train…