Search Results for author:
Found 6 papers, 2 papers with code
Investigating Failures to Generalize for Coreference Resolution Models
We investigate the extent to which errors of current coreference resolution models are associated with existing differences in operationalization across datasets (OntoNotes, PreCo, and Winogrande).
Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge
Transformer models pre-trained with a masked-language-modeling objective (e. g., BERT) encode commonsense knowledge as evidenced by behavioral probes; however, the extent to which this knowledge is acquired by systematic inference over the semantics of the pre-training corpora is an open question.
ADEPT: An Adjective-Dependent Plausibility Task
A false contract is more likely to be rejected than a contract is, yet a false key is less likely than a key to open doors.
Modeling Event Plausibility with Consistent Conceptual Abstraction
Understanding natural language requires common sense, one aspect of which is the ability to discern the plausibility of events.
Can a Gorilla Ride a Camel? Learning Semantic Plausibility from Text
Previous work has focused specifically on modeling physical plausibility and shown that distributional methods fail when tested in a supervised setting.
META-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation
Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that learn the value of a given policy, as well as algorithms which learn how to improve policies.
