Search Results for author:
Found 8 papers, 4 papers with code
Linearity of Relation Decoding in Transformer Language Models
Linear relation representations may be obtained by constructing a first-order approximation to the LM from a single prompt, and they exist for a variety of factual, commonsense, and linguistic relations.
Do We Still Need Clinical Language Models?
To investigate this question, we conduct an extensive empirical analysis of 12 language models, ranging from 220M to 175B parameters, measuring their performance on 3 different clinical tasks that test their ability to parse and reason over electronic health records.
Natural Language Descriptions of Deep Visual Features
Given a neuron, MILAN generates a description by searching for a natural language string that maximizes pointwise mutual information with the image regions in which the neuron is active.
Toward a Visual Concept Vocabulary for GAN Latent Space
A large body of recent work has identified transformations in the latent spaces of generative adversarial networks (GANs) that consistently and interpretably transform generated images.
Natural Language Descriptions of Deep Features
Given a neuron, MILAN generates a description by searching for a natural language string that maximizes pointwise mutual information with the image regions in which the neuron is active.
The Low-Dimensional Linear Geometry of Contextualized Word Representations
We show that a variety of linguistic features (including structured dependency relationships) are encoded in low-dimensional subspaces.
Program Synthesis from Visual Specification
Program synthesis is the process of automatically translating a specification into computer code.
