JHU Center for Language and Speech Processing

turking-bench

Web-grounded natural language instructions

CS-601-471-671-Sp24-Public

Repo of the programming homework for the course "CS 601.471/671 NLP: Self-supervised Models" - Spring 2024

Select-Topics-In-Multilingual-NLP

This is a wiki for keeping track of papers being presented during the Reading Group Select Topics in Multilingual Natural Language Processing

rockfish-tutorial

Confidence-Estimation-TrustNLP2023

Repo for the "Strength in Numbers: Estimating Confidence of Large Language Models by Prompt Agreement" paper in TrustNLP 2023 by Wightman et al.

Cost-Effective-Experiment

Scripts and docs that help us run cost effective experiment with OpenAI APIs

civil-unrest-case-study

Code and data from "Study of Manifestation of Civil Unrest on Twitter" W-NUT @ EMNLP 2021

CLSP-grid-onboarding

Exercise to teach a newcomer to the CLSP grid to set up their environment and run jobs

gpt2-narrative-decoding

Code for "Decoding Methods for Neural Narrative Generation"

JHU-CUT

Code, data, and models from "Civil Unrest on Twitter (CUT): A Dataset of Tweets to Support Research on Civil Unrest" EMNLP 2020 W-NUT

according-to

AnaloBench

This project focus on curating a robust analogical reasoning dataset for research and development.

Bernice-Twitter-encoder

carmen-wnut22-submission

clsp-pubs

The code used for crawling CLSP faculty publication from Semantic Scholar

Kreyol-MT

csci-601-771-self-supervised-models

docker-http-api-example

Example code for creating an HTTP API for an ML model (or similar) in Docker

Geo-Seq2seq-Twitter

Code for training and evaluating Geo-Seq2seq, a seq2seq approach to Twitter user geolocation. Published at ACL 2023.

slack_lm

Connect our internal LLM to Slack

NELLIE

Repository for NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning

prompt-format-grounding

reasoning_world_model