Timezone: »

 
Poster
e-SNLI: Natural Language Inference with Natural Language Explanations
Oana-Maria Camburu · Tim Rocktäschel · Thomas Lukasiewicz · Phil Blunsom

Tue Dec 04 02:00 PM -- 04:00 PM (PST) @ Room 210 #86
in Tue Poster Session B »

In order for machine learning to garner widespread public adoption, models must be able to provide interpretable and robust explanations for their decisions, as well as learn from human-provided explanations at train time. In this work, we extend the Stanford Natural Language Inference dataset with an additional layer of human-annotated natural language explanations of the entailment relations. We further implement models that incorporate these explanations into their training process and output them at test time. We show how our corpus of explanations, which we call e-SNLI, can be used for various goals, such as obtaining full sentence justifications of a model’s decisions, improving universal sentence representations and transferring to out-of-domain NLI datasets. Our dataset thus opens up a range of research directions for using natural language explanations, both for improving models and for asserting their trust

Keywords: Deep Learning · Natural Language Processing
[ Paper] 

Author Information

Oana-Maria Camburu (University of Oxford)
Tim Rocktäschel (University of Oxford)

Tim is a Researcher at Facebook AI Research (FAIR) London, an Associate Professor at the Centre for Artificial Intelligence in the Department of Computer Science at University College London (UCL), and a Scholar of the European Laboratory for Learning and Intelligent Systems (ELLIS). Prior to that, he was a Postdoctoral Researcher in Reinforcement Learning at the University of Oxford, a Junior Research Fellow in Computer Science at Jesus College, and a Stipendiary Lecturer in Computer Science at Hertford College. Tim obtained his Ph.D. from UCL under the supervision of Sebastian Riedel, and he was awarded a Microsoft Research Ph.D. Scholarship in 2013 and a Google Ph.D. Fellowship in 2017. His work focuses on reinforcement learning in open-ended environments that require intrinsically motivated agents capable of transferring commonsense, world and domain knowledge in order to systematically generalize to novel situations.

Thomas Lukasiewicz (University of Oxford)
Phil Blunsom (Oxford University)

More from the Same Authors