Douwe Kiela

Douwe is a Research Scientist at Facebook AI Research in New York. He received his Ph.D. and M.Phil. from the University of Cambridge. Prior to that, Douwe earned an undergraduate degree from Utrecht University with a double major in Cognitive Artificial Intelligence and Philosophy. He also earned a Master's degree in Logic at the University of Amsterdam's Institute for Logic, Language and Computation. He focuses on machine learning and natural language processing. Douwe's research interests lie in developing better models for language understanding and grounded language learning.

Douwe's Publications



Finding Generalizable Evidence by Learning to Convince Q&A Models

We propose a system that finds the strongest supporting evidence for a given answer to a question, using passage-based question-answering (QA) as a testbed. We train evidence agents to select the passage sentences that most convince a…

Ethan Perez, Siddharth Karamcheti, Rob Fergus, Jason Weston, Douwe Kiela, Kyunghyun Cho,



Countering Language Drift via Visual Grounding

Emergent multi-agent communication protocols are very different from natural language and not easily interpretable by humans. We find that agents that were initially pretrained to produce natural language can also experience detrimental…

Jason Lee, Kyunghyun Cho, Douwe Kiela,



Learning to Speak and Act in a Fantasy Text Adventure Game

We introduce a large-scale crowdsourced text adventure game as a research platform for studying grounded dialogue. In it, agents can perceive, emote, and act whilst conducting dialogue with other agents. Models and humans can both act as…

Jack Urbanek, Angela Fan, Siddharth Karamcheti, Saachi Jain, Samuel Humeau, Emily Dinan, Tim Rocktäschel, Douwe Kiela, Arthur Szlam, Jason Weston,