LIL Lab's repositories
cerealbar
Cereal Bar is a two-player web game designed for studying language understanding agents in collaborative interactions. This repository contains code for the game, a webapp hosting the game, the agent implementation, and recorded interactions in the game. http://lil.nlp.cornell.edu/cerealbar/
vgnsl_analysis
"What is Learned in Visually Grounded Neural Syntax Acquisition", Noriyuki Kojima, Hadar Averbuch-Elor, Alexander Rush and Yoav Artzi (ACL 2020)
geoquery-corpus
The GeoQuery corpus
kilogram-annotation-task
Task website for collecting tangram annotations from MTurk.
remote-teaching-setup
Remote teaching and talk recording setup
transformers-lmgen
🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
clif_cb
Continual learning for instruction following in CerealBar.