C
Christopher Clark
Researcher at Allen Institute for Artificial Intelligence
Publications - 43
Citations - 11310
Christopher Clark is an academic researcher from Allen Institute for Artificial Intelligence. The author has contributed to research in topics: Medicine & Diffusion MRI. The author has an hindex of 17, co-authored 31 publications receiving 9426 citations.
Papers
More filters
Proceedings ArticleDOI
Deep contextualized word representations
Matthew E. Peters,Mark Neumann,Mohit Iyyer,Matt Gardner,Christopher Clark,Kenton Lee,Luke Zettlemoyer +6 more
TL;DR: This paper introduced a new type of deep contextualized word representation that models both complex characteristics of word use (e.g., syntax and semantics), and how these uses vary across linguistic contexts (i.e., to model polysemy).
Posted Content
Deep contextualized word representations
Matthew E. Peters,Mark Neumann,Mohit Iyyer,Matt Gardner,Christopher Clark,Kenton Lee,Luke Zettlemoyer +6 more
TL;DR: This article introduced a new type of deep contextualized word representation that models both complex characteristics of word use (e.g., syntax and semantics), and how these uses vary across linguistic contexts (i.e., to model polysemy).
Proceedings ArticleDOI
Simple and Effective Multi-Paragraph Reading Comprehension
Christopher Clark,Matt Gardner +1 more
TL;DR: This article introduced a method of adapting neural paragraph-level question answering models to the case where entire documents are given as input, and showed that it is possible to significantly improve performance by using a modified training scheme that teaches the model to ignore nonanswer containing paragraphs.
Posted Content
BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions.
Christopher Clark,Kenton Lee,Ming-Wei Chang,Tom Kwiatkowski,Michael Collins,Kristina Toutanova +5 more
TL;DR: The authors study yes/no questions that are naturally occurring, meaning that they are generated in unprompted and unconstrained settings, and build a reading comprehension dataset, BoolQ, of such questions.
Proceedings ArticleDOI
Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases
TL;DR: This paper trains a naive model that makes predictions exclusively based on dataset biases, and a robust model as part of an ensemble with the naive one in order to encourage it to focus on other patterns in the data that are more likely to generalize.