esteng

regal_program_learning

miso_uds

ambiguous_vqa

calibration_metric

guiding-multi-step

Release for Guiding Multi-Step Rearrangement Tasks with Natural Language Instructions (CoRL 2021)

ambiguous_parsing

pragmatic_calibration

calibration_miso

curious-case-of-control

semantic_parsing_with_constrained_lm

Code to reproduce experiments in the paper "Constrained Language Models Yield Few-Shot Semantic Parsers" (EMNLP 2021).

nlu-incremental-symbol-learning

incremental symbol learning for natural language understanding

aclrollingreview

ACL Rolling Review website

al-folio

A beautiful, simple, clean, and responsive Jekyll theme for academics

allennlp-models

Officially supported AllenNLP models

annotation_hit

code-semparse

costar_dataset

Installable python package for the costar dataset. Work in progress.

decomp

The Universal Decompositional Semantics (UDS) dataset and the Decomp toolkit

drrn-scienceworld

ec

esteng.github.io

Personal webpage

Faithful-COT

Code and data accompanying our paper on arXiv "Faithful Chain-of-Thought Reasoning".

jiant

The jiant toolkit for general-purpose text understanding models

lamorel

Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).

lxmert

PyTorch code for EMNLP 2019 paper "LXMERT: Learning Cross-Modality Encoder Representations from Transformers".

ParlAI

A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

parlai_pointer

t5-scienceworld-cogai

task_oriented_dialogue_as_dataflow_synthesis

Code to reproduce experiments in the paper "Task-Oriented Dialogue as Dataflow Synthesis" (TACL 2020).

vagueness