Christopher Clark

I am a young investigator at the PRIOR team in AI2. I recently got my PhD from the University of Washington advised by Luke Zettlemoyer.

I am interested in machine learning and natural language processing. My recent work has been on preventing models from adopting naive heuristics that happen to work well on the training data, but are not fundamental to the target task. For example, preventing models from learning that sentences containing the word 'not' contradict any other sentence when doing textual entailment.


Don’t Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases
Christopher Clark, Mark Yatskar, Luke Zettlemoyer
In EMNLP 2019
[paper] [code]

BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions
Christopher Clark, Kenton Lee, Ming-Wei Chang, Tom Kwiatkowski, Michael Collins, Kristina Toutanova
In NAACL 2019
[paper] [dataset] [leaderboard]

Simple and Effective Multi-Paragraph Reading Comprehension
Christopher Clark, Matt Gradner
In ACL 2018
[paper] [code]

Deep Contextualized Word Representations
Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, Luke Zettlemoyer
In NAACL 2018
[paper] [website]

IKE - An Interactive Tool for Knowledge Extraction
Bhavana Dalvi, Sumithra Bhakthavatsalam, Chris Clark, Peter Clark, Oren Etzioni, Anthony Fader, Dirk Groeneveld
In AKBC at NAACL 2016
[paper] [website] [code]

PDFFigures 2.0: Mining Figures from Research Papers
Christopher Clark, Jieyu Zhao, Mark Yatskar, Kai-Wei Chang, Vicente Ordonez.
In JCDL 2016
[paper] [website] [code]

Looking Beyond Text: Extracting Figures, Tables, and Captions from Computer Science Papers
Christopher Clark, Santosh Divvala
In Workshop on Scholarly Big Data at AAAI 2015
[paper] [website] [code]

Training Deep Convolutional Neural Networks to Play Go
Christopher Clark, Amos Storkey
In ICML 2015
[paper] [demo] [press]


CSE 424
Paul G. Allen Center for Computer Science & Engineering
Email: csquared [at] cs [dot] washington [dot] edu