13 citations · 25 across the 5 of their papers we have counts for
7 papers
ImPaKT: A Dataset for Open-Schema Knowledge Base Construction
Luke Vilnis, Zach Fisher, Bhargav Kanagal +2
Large language models have ushered in a golden age of semantic parsing. The seq2seq paradigm allows for open-schema and abstractive attribute and relation extraction given only sma…
LogicInference: A New Dataset for Teaching Logical Inference to seq2seq Models
Santiago Ontanon, Joshua Ainslie, Vaclav Cvicek +1
Machine learning models such as Transformers or LSTMs struggle with tasks that are compositional in nature such as those involving reasoning/inference. Although many datasets exist…
Making Transformers Solve Compositional Tasks
Santiago Ontañón, Joshua Ainslie, Vaclav Cvicek +1
Several studies have reported the inability of Transformer models to generalize compositionally, a key type of generalization in many NLP tasks such as semantic parsing. In this pa…
Evaporating Black Holes Coupled to a Thermal Bath
Hong Zhe Chen, Zachary Fisher, Juan Hernandez +2
We study the doubly holographic model of [arXiv:1908.10996] in the situation where a black hole in two-dimensional JT gravity theory is coupled to an auxiliary bath system at arbit…
Information Flow in Black Hole Evaporation
Hong Zhe Chen, Zachary Fisher, Juan Hernandez +2
Recently, new holographic models of black hole evaporation have given fresh insights into the information paradox [arXiv:1905.08255, arXiv:1905.08762, arXiv:1908.10996]. In these m…
A Semiclassical, Entropic Proof of a Weak Gravity Conjecture
Zachary Fisher, Christopher J. Mogni
We present a semiclassical proof of the weak gravity conjecture in spacetime dimensions for scalar matter gauged under a gauge group. We compute the non-perturbati…