• Publications
  • Influence
The Curious Case of Neural Text Degeneration
TLDR
By sampling text from the dynamic nucleus of the probability distribution, which allows for diversity while effectively truncating the less reliable tail of the distribution, the resulting text better demonstrates the quality of human text, yielding enhanced diversity without sacrificing fluency and coherence. Expand
Learning to Write with Cooperative Discriminators
TLDR
Human evaluation demonstrates that text generated by the RNN system is preferred over that of baselines by a large margin and significantly enhances the overall coherence, style, and information content of the generated text. Expand
Verb Physics: Relative Physical Knowledge of Actions and Objects
TLDR
An approach to infer relative physical knowledge of actions and objects along five dimensions (e.g., size, weight, and strength) from unstructured natural language text is presented. Expand
Robot Programming by Demonstration with Crowdsourced Action Fixes
TLDR
This paper proposes a PbD framework in which the end-user provides an initial seed demonstration, and then the robot searches for scenarios inWhich the action will not work and requests the crowd to fix the action for these scenarios. Expand
Neural Naturalist: Generating Fine-Grained Image Comparisons
TLDR
A new model is proposed called Neural Naturalist that uses a joint image encoding and comparative module to generate comparative language, and the results indicate promising potential for neural models to explain differences in visual embedding space using natural language. Expand
Thinking Like a Skeptic: Defeasible Inference in Natural Language
TLDR
From Defeasible NLI, both a classification and generation task for defeasible inference are developed, and it is demonstrated that the generation task is much more challenging. Expand
Robot Programming by Demonstration with situated spatial language understanding
TLDR
A natural language based interface for PbD that removes requirements and enables hands-free programming and takes a natural language command and the current world state to infer the intended movement command and its parametrization. Expand
Accelerating imitation learning through crowdsourcing
TLDR
This work presents a new goal-based imitation learning framework which utilizes crowdsourcing as a major source of human demonstration data and shows how the robot can use this knowledge to support human-robot collaboration tasks such as goal inference through object-part classification and missing-part prediction. Expand
Do Neural Language Representations Learn Physical Commonsense?
TLDR
While recent advancements of neural language models have demonstrated strong performance on various types of natural language inference tasks, this study based on a dataset of over 200k newly collected annotations suggests that neural language representations still only learn associations that are explicitly written down. Expand
Social Chemistry 101: Learning to Reason about Social and Moral Norms
TLDR
A new conceptual formalism to study people's everyday social norms and moral judgments over a rich spectrum of real life situations described in natural language and a model framework, Neural Norm Transformer, learns and generalizes Social-Chem-101 to successfully reason about previously unseen situations, generating relevant (and potentially novel) attribute-aware social rules-of-thumb. Expand
...
1
2
3
...